Freelance AI Agent Engineers in Bengaluru

Freelance AI Agent Engineers in BengaluruFreelance AI Agent Engineers in Bengaluru

Projects People

Bengaluru, India

AI Agents & Custom CRM/ERP | Voice, WhatsApp, SMS Automation

AI Agents & Custom CRM/ERP | Voice, WhatsApp, SMS Automation

Cover image for Bilingual Arabic/English AI Voice Agent for a Dubai Brokerage

Bilingual Arabic/English AI Voice Agent for a Dubai Brokerage

0

1

Cover image for Speed-to-Lead AI Agent for US Real-Estate Brokerages

Speed-to-Lead AI Agent for US Real-Estate Brokerages

0

1

Cover image for Filingo: SaaS Workspace and 25 Tools for CA Firms

Filingo: SaaS Workspace and 25 Tools for CA Firms

0

1

Cover image for Trading ERP That Replaced an 18-Sheet Excel Workbook

Trading ERP That Replaced an 18-Sheet Excel Workbook

0

1

AI Agent Engineer(2)

proBengaluru, India

Expert in Bubble & AI No-Code Solutions

8: Followers

expert

Expert in Bubble & AI No-Code Solutions

Cover image for AI-Solution for UK EdTech

AI-Solution for UK EdTech

0

11

Cover image for Sabbath AI | Voice-Driven Event Communication Platform

Sabbath AI | Voice-Driven Event Communication Platform

0

10

Cover image for Pawsport — Pet Travel Compliance Platform

Pawsport — Pet Travel Compliance Platform

0

11

Cover image for Appointment Manager for Real Estate Agents

Appointment Manager for Real Estate Agents

0

23

AI Agent Engineer(1)

Sarath Chandran

Bengaluru, India

AI Agent Developer | LLM | TypeScript | Frontend Architect

New to Contra

AI Agent Developer | LLM | TypeScript | Frontend Architect

Cover image for miniSara Personal AI OS —

miniSara Personal AI OS — AI-Powered Personal Assistant miniSara Personal AI OS is an AI-powered personal productivity platform designed to bring conversations, AI agents, personal knowledge, tasks, projects, automation, and integrations into one intelligent workspace. The platform is designed around a Think → Remember → Plan → Act workflow, allowing AI agents to understand context, retrieve relevant knowledge, plan tasks, use tools, and execute approved actions. Key capabilities: AI Agent orchestration Personal knowledge and memory AI-powered task and project management Workflow automation Tool calling and integrations Multi-model AI support Local-first and privacy-focused architecture Permission and approval-based actions Cross-platform experience My role: Product architecture, AI agent architecture, TypeScript engineering, orchestration, tool systems, UX architecture, and end-to-end product development.

1

77

Cover image for Minova Systems -

Minova Systems - Accessibility + SaaS + Frontend Architecture Minova Systems is a technology initiative focused on building modern, accessible, and scalable digital products for businesses. The platform provides professional web accessibility auditing and remediation services, helping organizations identify and resolve WCAG accessibility issues across their web applications. The project combines frontend engineering, accessibility engineering, SaaS architecture, automated auditing, and AI-assisted development to create practical tools that help teams improve usability, compliance, and overall product quality. Key highlights Web Accessibility & WCAG — Accessibility auditing and remediation workflows Angular & TypeScript — Scalable frontend architecture and reusable components SaaS Architecture — Designed for multi-client and subscription-based services Automated Accessibility Analysis — Identify common accessibility issues efficiently Accessibility Remediation — Practical recommendations and developer-focused fixes Modern UI Engineering — Responsive, accessible, performance-focused interfaces AI-Assisted Development — Using modern AI tools to accelerate development and engineering workflows Cloud Deployment — Modern cloud-ready architecture and deployment practices

1

61

Cover image for miniSara Studio — AI Video

miniSara Studio — AI Video & VFX Creation Platform miniSara Studio is a mobile-first AI video creation platform designed to help creators turn ideas, images, and reference media into engaging videos. The platform supports multiple AI generation workflows including Text-to-Video, Image-to-Video, Reference Image-to-Video, Video-to-Video, Motion Transfer, VFX, Character workflows, and AI-powered media transformation. Built with a local-first architecture, miniSara Studio allows users to create and manage projects and media locally while providing an architecture that can support cloud-based AI generation providers and scalable backend services. The product is designed with a mobile-first UX, reusable architecture, asynchronous generation jobs, provider-independent AI pipelines, project management, media libraries, export/share workflows, and extensible generation modes. My role: Product architecture, frontend architecture, mobile application development, AI generation architecture, UX implementation, domain modeling, local-first storage, and engineering of the generation pipeline.

1

80

Cover image for miniSara AI Agent - AI

miniSara AI Agent - AI Agents, LLM, Tool Calling, Agent Orchestration miniSara AI Agent is a production-oriented AI coding agent designed to help developers understand, modify, and automate software projects through natural-language interaction. I designed and developed the agent architecture with a strong focus on reliability, security, extensibility, and developer experience. The system includes an LLM provider abstraction supporting multiple providers, secure tool execution, agent orchestration, streaming responses, approval-based mutations, verification, and self-healing workflows. Key capabilities: AI agent orchestration and multi-step reasoning workflows LLM provider abstraction for OpenAI, Anthropic, and Ollama Secure tool-calling and controlled tool execution Streaming AI responses and real-time tool activity Approval workflows for potentially destructive changes Automated verification and recovery/self-healing TypeScript/Node.js architecture with strong automated test coverage Cross-platform executable and development-environment support Tech: TypeScript, Node.js, LLMs, OpenAI, Anthropic, Ollama, Tool Calling, Streaming, Agent Orchestration, AI Engineering.

1

87

AI Agent Engineer(1)

Bengaluru, India

AI Data Analyst | Power BI & Python | Automated Reports

7: Followers

AI Data Analyst | Power BI & Python | Automated Reports

Cover image for Built something I'm pretty proud

Built something I'm pretty proud of — Data Detective An AI-powered anomaly investigation tool that turns dry data analysis into a noir detective case. Under the hood: → Claude + 14 custom MCP tools → Isolation Forest for anomaly detection → Pearson correlation analysis → Results presented as an actual investigation report No spreadsheets. No jargon. Just: "The suspect is outlier #47. Here's the evidence." Live here → [https://claude.ai/public/artifacts/f8117dff-b531-4f31-8862-2a86a77137c2] Full MCP server → https://github.com/Varu4/prodata-ai-mcp #contralabs #AI #dataanalysis

2

4

350

Cover image for From Chaos to Clarity: Healthcare

From Chaos to Clarity: Healthcare Dashboard in Power BI 1. Clean and interactive Power BI dashboard for tracking patient trends, hospital performance, and key healthcare metrics in one place. 2. A modern healthcare analytics dashboard built in Power BI to monitor admissions, diseases, and operational efficiency. 3. Turn raw healthcare data into meaningful insights with this intuitive and fully interactive Power BI dashboard.

0

100

Cover image for ProData AI — Automated Data

ProData AI — Automated Data Science Platform Built ProData AI, an automated data science platform developed entirely with Streamlit. It is designed to help users transform raw datasets into actionable business insights in seconds. 🚀 What it does One-Click Mode Upload any CSV or Excel file and the full pipeline runs automatically in under 30 seconds: Data cleaning & preprocessing AutoML (6 models trained simultaneously) 30-day forecasting using Prophet Business driver analysis with Explainable AI (XAI) AI-generated insights using Anthropic Claude PDF report generation Manual Mode Provides full control over each stage of the data science workflow for advanced users. 🛠 Tech Stack Streamlit — complete UI and app framework scikit-learn — AutoML pipeline Prophet — time-series forecasting Anthropic Claude API — AI insights & chat Plotly — interactive visualizations fpdf2 — PDF report generation Ideal for: business analysts startups small businesses automated reporting workflows freelance analytics projects Open to freelance collaborations and custom dashboard / AI reporting solutions.

5

4

381

Cover image for AI Data Scientist

AI Data Scientist

1

4

AI Agent Engineer(1)

Bengaluru, India

Production ML that turns messy data into decisions!!

New to Contra

Production ML that turns messy data into decisions!!

Cover image for NeuroVision AI is a clinical-grade

NeuroVision AI is a clinical-grade platform that detects neurological gait disorders from walking videos using computer vision and AI. It extracts key biomechanical parameters - cadence, symmetry, tremor index, and freezing episodes, via MediaPipe pose estimation and Isolation Forest anomaly detection, trained on established datasets including DaphNet and PhysioNet GaitPDB. The system delivers AI-powered differential diagnoses, real-time clinical Q&A, and spoken voice reports, all within 60 seconds of video input.

0

62

Cover image for Day one on Contra. New

Day one on Contra. New to the platform, not to the work. I build production ML systems that turn messy data into decisions, and I build the product around them. Where I am strongest: Production ML: risk scoring, prediction, ranking, computer vision Data engineering: pipelines that turn raw, scattered data into reliable features LLM apps: RAG, structured prompting, and evaluation that keeps them honest And I built the full product around it, too: FastAPI and backend services, React and Next.js frontends, dashboards, mobile, and workflow automation when a project needs it. I like owning the whole path from data to a working thing people use. Most builders stop at the demo. I take it to be deployed, monitored, and actually earning its keep. I also provide automation services for your Saas that you don't wanna waste your hours on. Starting today, I am open to work. Independent contracts, remote, a full build, or one piece of one. Startups and small teams turning an idea into a real product are exactly who I want to work with. My projects are on my profile if you want to see how I think before we talk. A piece of my playground work done within hours is posted too. #MachineLearning #AIEngineer #LLM #FastAPI #React #Nextjs #Contra

1

58

Cover image for TechnovaHub chatbot is a branded

TechnovaHub chatbot is a branded AI-powered customer assistant built with React and Node.js, featuring real-time streaming responses via Google Gemini API. It supports bilingual interaction (English and Tamil), voice input, lead capture, and smart intent detection for courses and pricing. The chatbot includes a secure backend proxy, XSS sanitization, and a modular architecture with 57 automated tests ensuring production-grade reliability.

1

84

Cover image for VitalFlow HeartGuard is a cardiovascular

VitalFlow HeartGuard is a cardiovascular risk analytics platform built on the Framingham Heart Study dataset (4,238 patients). It trains three Apache Spark ML models — Logistic Regression, Random Forest, and Gradient Boosted Trees — to predict 10-year coronary heart disease risk. The platform features a FastAPI backend with JWT auth, live what-if analysis, counterfactual interventions, model drift detection, and PDF report generation. A React dashboard visualizes EDA, ROC curves, feature importance, and patient risk trends.

0

76

AI Agent Engineer(1)

Bengaluru, India

Full Stack AI Engineer shipping fast SaaS MVPs

New to Contra

Full Stack AI Engineer shipping fast SaaS MVPs

Cover image for Ever watched an AI write

Ever watched an AI write bad SQL, instantly realize its mistake, and rewrite it perfectly—all without human intervention? Over the weekend, I built the Autonomous Data Analyst Agent. It doesn’t just translate natural language to SQL; it actively debugs itself. 𝗧𝗵𝗲 𝗣𝗿𝗼𝗯𝗹𝗲𝗺: Enterprises want AI to query their proprietary databases, but LLMs often hallucinate columns or mess up syntax. 𝗧𝗵𝗲 𝗦𝗼𝗹𝘂𝘁𝗶𝗼𝗻: I engineered a Self-Correcting Reflection Loop using LangGraph. Here’s what happens under the hood: 1️⃣ You ask a complex question in plain English. 2️⃣ The LLM generates DuckDB-flavored SQL. 3️⃣ The Executor node runs it securely in a local container. 4️⃣ 🔄 𝗧𝗵𝗲 𝗠𝗮𝗴𝗶𝗰: If DuckDB throws a parser error, the Reflection node catches it, feeds the error trace back to the LLM, and auto-corrects the query. 5️⃣ Once successful, a Python agent generates a Matplotlib visualization, streaming everything to a sleek Next.js dark-mode UI. Plus, I integrated LangGraph MemorySaver, allowing the agent to retain context for human-like follow-up questions. 𝗧𝗲𝗰𝗵 𝗦𝘁𝗮𝗰𝗸: Next.js, FastAPI, LangGraph, DuckDB, Groq (Llama-3), Docker Compose. Everything is fully containerized and open-source. Drop a ⭐ on the repo and let me know what you think! 𝗚𝗶𝘁𝗛𝘂𝗯 𝗥𝗲𝗽𝗼: https://lnkd.in/ddnE9rgq (https://lnkd.in/ddnE9rgq)hashtag#AI (https://www.linkedin.com/search/results/all/?keywords=%23ai&origin=HASH_TAG_FROM_FEED) hashtag#LangGraph (https://www.linkedin.com/search/results/all/?keywords=%23langgraph&origin=HASH_TAG_FROM_FEED) hashtag#DataEngineering (https://www.linkedin.com/search/results/all/?keywords=%23dataengineering&origin=HASH_TAG_FROM_FEED) hashtag#Nextjs (https://www.linkedin.com/search/results/all/?keywords=%23nextjs&origin=HASH_TAG_FROM_FEED) hashtag#FastAPI (https://www.linkedin.com/search/results/all/?keywords=%23fastapi&origin=HASH_TAG_FROM_FEED) hashtag#Docker (https://www.linkedin.com/search/results/all/?keywords=%23docker&origin=HASH_TAG_FROM_FEED) hashtag#MachineLearning (https://www.linkedin.com/search/results/all/?keywords=%23machinelearning&origin=HASH_TAG_FROM_FEED) hashtag#OpenSource (https://www.linkedin.com/search/results/all/?keywords=%23opensource&origin=HASH_TAG_FROM_FEED)

1

47

Cover image for 𝗛𝗲𝗮𝗱𝗹𝗶𝗻𝗲: What started as a

𝗛𝗲𝗮𝗱𝗹𝗶𝗻𝗲: What started as a simple B2C expense tracker has officially pivoted into a fully automated B2B Financial SaaS. Introducing 𝗙𝗶𝗻𝗮𝗻𝗦𝗺𝗮𝗿𝘁. 𝗕𝗼𝗱𝘆: I realized that startup founders and agency owners spend countless hours manually categorizing bank statements and tracking operational costs. I wanted to build a solution that entirely automates this bookkeeping process. Building the core feature—an "𝐀𝐈 𝐁𝐚𝐧𝐤 𝐒𝐭𝐚𝐭𝐞𝐦𝐞𝐧𝐭 𝐏𝐚𝐫𝐬𝐞𝐫"—was one of the toughest technical challenges I’ve faced. I hit a massive roadblock when Next.js 14’s Webpack bundler kept breaking legacy PDF OCR libraries in serverless environments. Instead of compromising on the feature, I completely re-architected the data pipeline: • I bypassed Webpack issues by implementing pdf2json on a strict Node.js runtime for secure, server-side text extraction. • I piped this raw text into Groq’s LLaMA-3.1-8b model using highly optimized system prompts. • The result? Lightning-fast, deterministic extraction that converts raw PDF text into perfectly structured JSON arrays. Now, users can drag-and-drop a PDF statement, and the AI instantly categorizes every transaction (Infrastructure, Payroll, Revenue) into a 'pending' staging area. Once approved, the data flows securely via Drizzle ORM into a Neon PostgreSQL database, updating real-time Recharts dashboards. 𝑻𝒆𝒄𝒉 𝑺𝒕𝒂𝒄𝒌: Next.js App Router, Tailwind CSS, Shadcn UI, Clerk Auth, Drizzle ORM, Neon DB, and Groq SDK. 𝗪𝗵𝗮𝘁'𝘀 𝗡𝗲𝘅𝘁? I am currently looking for my next full-time opportunity as a Full Stack Developer (based in Bangalore or anywhere). I am also actively taking on 𝗳𝗿𝗲𝗲𝗹𝗮𝗻𝗰𝗲 𝗽𝗿𝗼𝗷𝗲𝗰𝘁𝘀. If you are a founder or agency looking to build scalable, AI-integrated SaaS MVPs without the technical headache, let's connect. Check out the demo video below to see the AI parser in action! 🔗 Live Project: https://lnkd.in/gSNu3cAK (https://lnkd.in/gSNu3cAK)hashtag#BuildInPublic (https://www.linkedin.com/search/results/all/?keywords=%23buildinpublic&origin=HASH_TAG_FROM_FEED) hashtag#Nextjs (https://www.linkedin.com/search/results/all/?keywords=%23nextjs&origin=HASH_TAG_FROM_FEED) hashtag#FullStackDevelopment (https://www.linkedin.com/search/results/all/?keywords=%23fullstackdevelopment&origin=HASH_TAG_FROM_FEED) hashtag#SaaS (https://www.linkedin.com/search/results/all/?keywords=%23saas&origin=HASH_TAG_FROM_FEED) hashtag#AI (https://www.linkedin.com/search/results/all/?keywords=%23ai&origin=HASH_TAG_FROM_FEED) hashtag#Groq (https://www.linkedin.com/search/results/all/?keywords=%23groq&origin=HASH_TAG_FROM_FEED) hashtag#PostgreSQL (https://www.linkedin.com/search/results/all/?keywords=%23postgresql&origin=HASH_TAG_FROM_FEED) hashtag#WebDevelopment (https://www.linkedin.com/search/results/all/?keywords=%23webdevelopment&origin=HASH_TAG_FROM_FEED) hashtag#FreelanceDeveloper (https://www.linkedin.com/search/results/all/?keywords=%23freelancedeveloper&origin=HASH_TAG_FROM_FEED) hashtag#Hiring (https://www.linkedin.com/search/results/all/?keywords=%23hiring&origin=HASH_TAG_FROM_FEED)

1

55

Cover image for I recently architected and built

I recently architected and built VedaAI Assessment Creator, a personal project designed to transform unstructured notes and files (PDFs, DOCX) into highly structured, curriculum-aligned exam papers. Building enterprise-grade applications at scale requires looking beyond simply making API calls. For this build, I wanted to focus entirely on non-blocking architectures and deterministic AI outputs. Here is a breakdown of the technical decisions: Asynchronous Workers: Instead of blocking the main HTTP thread during heavy file parsing and AI inference, I implemented a distributed task queue using BullMQ and Upstash Serverless Redis. The Express API responds in under 100ms, while background workers handle the heavy lifting. Deterministic AI: I opted for Groq (Llama-3.3-70b) utilizing its JSON mode. The sub-500ms inference time and guaranteed schema compliance eliminated the need for complex post-processing validation. Real-Time Synchronization: A WebSocket setup broadcasts job completion events, updating the Next.js frontend instantly without relying on inefficient polling. Database & State: MongoDB Atlas handles ACID transactions for complex document updates, while Zustand manages lightweight, atomic state slices on the frontend. I also built in granular question regeneration—allowing users to re-run isolated inference calls for single questions without replacing the entire paper—and print-ready A4 PDF exports. Designing this kind of scalable infrastructure directly supports my ongoing deep dive into advanced AI and machine learning systems. You can check out the Live Link here: https://lnkd.in/geAXUtHC . I would love to hear how others are handling asynchronous AI tasks in production!

1

50

Cover image for 𝗛𝗲𝗮𝗱𝗹𝗶𝗻𝗲: Most Voice AI agents

𝗛𝗲𝗮𝗱𝗹𝗶𝗻𝗲: Most Voice AI agents still feel like glorified walkie-talkies. So I built one that actually listens like a human. Most voice bots today follow a rigid, linear loop: You speak ➔ Wait ➔ Bot speaks. If you dare interrupt them mid-sentence? They either completely ignore you or their context buffer gets totally mangled. 𝗧𝗼 𝘀𝗼𝗹𝘃𝗲 𝘁𝗵𝗶𝘀, I engineered Astra Duplex Agent — a sub-50ms, ultra-low latency, full-duplex conversational Voice AI built to handle natural human interruptions seamlessly. Here is what went into building the architecture under the hood: True Full-Duplex WebSockets: Built on FastAPI, allowing real-time bi-directional audio streaming instead of turn-based HTTP requests. Edge Voice Activity Detection (VAD): Deployed Silero VAD using ONNX Runtime to catch user barge-ins at the edge with near-zero overhead. LangGraph State Machine: Instead of a simple monolithic script, the conversation logic is modeled as a state graph, giving precise control over execution flow. Partial State Tracking & Memory Persistence: This was the trickiest part. When an interruption happens, Astra doesn't just stop audio playback — an async kill-switch halts Groq's LLaMA-3.1 mid-token, calculates the exact partial sentence actually spoken by the TTS, and saves only that partial context to an Upstash Redis buffer. Sub-50ms Inference & Streaming: Leveraged Groq LPU (LLaMA-3.1 + Whisper Large v3) paired with ElevenLabs Turbo v2.5 streaming. The result? An agent that you can interrupt mid-thought, change topics with on the fly, and ask follow-up questions without it losing historical context. Containerized with Docker and live on Render & Vercel. Check out the full architecture & live demo below! https://lnkd.in/eC6yak3i (https://lnkd.in/eC6yak3i)https://lnkd.in/eN38HGZD (https://lnkd.in/eN38HGZD)#VoiceAI (https://www.linkedin.com/search/results/all/?keywords=%23voiceai&origin=HASH_TAG_FROM_FEED) #GenerativeAI (https://www.linkedin.com/search/results/all/?keywords=%23generativeai&origin=HASH_TAG_FROM_FEED) #LangGraph (https://www.linkedin.com/search/results/all/?keywords=%23langgraph&origin=HASH_TAG_FROM_FEED) #SystemDesign (https://www.linkedin.com/search/results/all/?keywords=%23systemdesign&origin=HASH_TAG_FROM_FEED) #FastAPI (https://www.linkedin.com/search/results/all/?keywords=%23fastapi&origin=HASH_TAG_FROM_FEED) #MachineLearning (https://www.linkedin.com/search/results/all/?keywords=%23machinelearning&origin=HASH_TAG_FROM_FEED) #WebSockets (https://www.linkedin.com/search/results/all/?keywords=%23websockets&origin=HASH_TAG_FROM_FEED) #Python (https://www.linkedin.com/search/results/all/?keywords=%23python&origin=HASH_TAG_FROM_FEED) #AIENGINEERING (https://www.linkedin.com/search/results/all/?keywords=%23aiengineering&origin=HASH_TAG_FROM_FEED)

1

67

AI Agent Engineer(1)

Vasundhhara Katoch

Bengaluru, India

AI Engineer delivering products from 0 to scale

New to Contra

AI Engineer delivering products from 0 to scale

Cover image for AI Task Creation for Terminal-Bench

AI Task Creation for Terminal-Bench

0

3

Cover image for Khoros Iris Web Application Development

Khoros Iris Web Application Development

0

2

Cover image for Enhancements to Maestro for Parallel Software Sessions

Enhancements to Maestro for Parallel Software Sessions

0

2

Cover image for Personal Knowledge Model Development

Personal Knowledge Model Development

0

4

AI Agent Engineer(1)

Siddharath Narayan

Bengaluru, India

GenAI & ML Engineer | Research Assistant at IISc | IITian

GenAI & ML Engineer | Research Assistant at IISc | IITian

Cover image for Mood-Based Music Generator

Mood-Based Music Generator

0

7

Cover image for Deep Learning Framework for Seismic Image Analytics

Deep Learning Framework for Seismic Image Analytics

0

5

Cover image for 3D Solar System Simulation for National Space Day Hackathon

3D Solar System Simulation for National Space Day Hackathon

0

6

Placeholder project card media

View more →

AI Agent Engineer(1)