Freelancers using AWS in Ghaziabad

Freelancers using AWS in GhaziabadFreelancers using AWS in Ghaziabad

Projects People

AKASH VASHISHTHA

proDelhi, India

Versatile Fullstack Engineer | Web & Mobile Expert

$50k+: Earned

5x: Hired

5.0: Rating

112: Followers

Top

Versatile Fullstack Engineer | Web & Mobile Expert

Cover image for Realm - Social Media Platform for Music Producers and Artists

Realm - Social Media Platform for Music Producers and Artists

1

138

Cover image for TestBest | LSAT® Prep & Tutoring

TestBest | LSAT® Prep & Tutoring

2

156

Cover image for Légacie Phase 1

Légacie Phase 1

0

20

Cover image for AI Platform Stabilization and Enhancement for Kaie

AI Platform Stabilization and Enhancement for Kaie

3

114

New Delhi, India

Backend Engineer, API Dev & Databases 🚀

Backend Engineer, API Dev & Databases 🚀

Cover image for Travo Channel & Travo AI (acq by Spyne AI)

Travo Channel & Travo AI (acq by Spyne AI)

0

6

Cover image for Pet Perfect MVP

Pet Perfect MVP

0

7

Cover image for Awen <> Finance Products

Awen <> Finance Products

0

18

Placeholder project card media

View more →

maxGhaziabad, India

Senior Product Designer & Full-Stack Partner

$25k+: Earned

11x: Hired

4.9: Rating

162: Followers

expert

expert

+2

Senior Product Designer & Full-Stack Partner

Cover image for Enterprise HR Platform Web and Mobile Overhaul

Enterprise HR Platform Web and Mobile Overhaul

1

14

Cover image for Total Protect | Website Redesign, Framer Build & SEO Migration

Total Protect | Website Redesign, Framer Build & SEO Migration

0

15

Cover image for Tropos - AI Visuals & Framer Website Design

Tropos - AI Visuals & Framer Website Design

5

159

Luxury Automotive Brand Website Redesign and AI Media Strategy

1

59

Building MVPs for startup founders with clean UX in a week.

1x: Hired

5.0: Rating

60: Followers

Building MVPs for startup founders with clean UX in a week.

Cover image for Regenix - Healthcare System Modernization for Regenix

Regenix - Healthcare System Modernization for Regenix

0

5

Cover image for Reqwest - Designing an Efficient API Testing Platform

Reqwest - Designing an Efficient API Testing Platform

3

6

Cover image for SpongebobLabs - AI Research Lab Website Development

SpongebobLabs - AI Research Lab Website Development

1

8

Cover image for SaaSking AI - Enterprise Website Redesign

SaaSking AI - Enterprise Website Redesign

0

5

I build production AI agents that automate real workflows

I build production AI agents that automate real workflows

Cover image for Built an LLM-powered question-answering application

Built an LLM-powered question-answering application that lets users ask natural-language questions over large document corpora and get accurate, grounded answers, instead of manually searching through documents for the right section. Designed and built the full RAG pipeline independently, from document ingestion through to answer generation, as a technical demonstration of production-grade retrieval-augmented generation using AWS-native tooling. Key Challenges: Documents exceeding token limits: Large source documents couldn't be fed directly into the LLM's context window, so they had to be broken down without losing meaning or context across chunks. Finding the right context: With a large corpus, the system needed to reliably surface the specific chunks relevant to a given question, not just the most textually similar ones. Grounded, accurate answers: Answers had to be based on the actual retrieved content, not the model's general knowledge, to avoid confidently wrong responses. Working within a managed AWS ecosystem: Embeddings, storage, and generation all needed to work together cleanly using Bedrock-native models rather than a patchwork of external services. Approach: Document loading and chunking Processed large documents into manageable chunks sized to stay within model token limits while preserving enough context for coherent retrieval. Vector embeddings with Amazon Titan Generated vector embeddings for each document chunk using Amazon Titan, capturing semantic meaning rather than just keyword overlap. Vector storage and retrieval Stored the embeddings in a vector database, enabling fast similarity search to pull the most relevant chunks for any given question. RAG-based answer generation with Claude on Bedrock When a question comes in, the system retrieves the relevant chunks and passes them as context to Anthropic Claude via Amazon Bedrock, which generates an answer grounded in the retrieved content rather than relying on parametric memory alone. Results & Impact: Accurate, source-grounded answers over document corpora too large to fit in a single context window. A scalable retrieval architecture that separates document processing, embedding, and generation, so any of the three can be swapped or scaled independently. A fully AWS-native RAG pipeline, demonstrating fluency with Bedrock's embedding and generation models working together in production patterns. Tech Stack Python · LangChain · AWS Bedrock · Amazon Titan · Anthropic Claude · FAISS DB

1

82

Cover image for Built and maintained a HIPAA

Built and maintained a HIPAA compliant production medical AI scribe system that uses multi-step LLM agents to extract clinical entities directly from physician-patient conversations and turn them into structured medical notes, cutting down the manual transcription work clinicians used to do after every visit. Multi-stage clinical workflow: Documentation, coding, and review each have different logic and conditional paths, and the system needed to branch correctly between them without losing context. Clinical accuracy: Generated notes had to be grounded in real patient history and clinical guidelines, not just plausible-sounding text. Production reliability: As a live system handling real conversations, every agent run needed to be observable, debuggable, and monitored for cost and latency in real time. Non-technical requirements gathering: Clinical needs had to be captured accurately from stakeholders without a technical background and translated into precise agent logic. Approach: Stateful agent orchestration with LangGraph Designed LangGraph-based agent workflows with conditional branching, allowing the system to move correctly across documentation, coding, and review stages based on conversation content. Context-grounded note generation with RAG Built a RAG pipeline on AWS Bedrock with embeddings, so every generated note is grounded in the patient's actual history and relevant clinical guidelines rather than generic output. Full production observability Integrated Langfuse across all agent runs to track token usage, latency, and model KPIs, giving the team visibility into system health and cost in production, not just at build time. Clinical stakeholder collaboration Ran requirements sessions directly with clinical staff, converting their documentation needs into concrete agent behavior specs and validation criteria. Results & Impact: ~40% reduction in manual transcription time for clinicians using the system. Clinically grounded output, with notes tied to real patient history and guidelines instead of unsupported generation. Full production observability, with token usage, latency, and model performance tracked continuously. A workflow clinicians could trust, built through direct collaboration rather than a black-box handoff. Provided Services & Solutions: 📌 AI Agent Development (LangGraph) 📌 RAG Pipeline Development (AWS Bedrock) 📌 LLM Observability (Langfuse) 📌 Cloud Infrastructure (AWS Lambda, S3, DynamoDB) 📌 Stakeholder Requirements Translation 📌 Production ML Systems Tech Stack Python · LangChain · LangGraph · AWS (Bedrock, Lambda, S3, DynamoDB) · Langfuse · TypeScript · REST APIs

2

81

Cover image for My submission for replitbuildathon. Features

My submission for replitbuildathon. Features an AI agent that answers inbound leads in seconds, qualifies them against your rules, and books the appointment — rebrandable for a new client in about a minute. Most small businesses lose leads to silence. Someone lands on the site at 9pm, fills nothing in, and leaves. Frontdesk is the agent that catches them. It greets the visitor, works through the qualifying questions you defined, scores what it hears out of 100, books the appointment, and hands the team a lead with the transcript and a follow-up email already drafted. The reason it's a template and not a product: it's built to be rebranded. Set a logo and two colours in Brand Studio and the entire app, the chat widget, and the design system documentation retint together, because they all read the same tokens. Agencies fork it once per client. Applying a preset doesn't recolour the same install: it opens a different one, with its own agency name, business name and greeting. Checkout the app here: https://frontdeskzip--SuyashDubey3.replit.app

2

90

Cover image for Built a virtual try-on application

Built a virtual try-on application that lets users try on garments over WhatsApp. A user sends a photo through WhatsApp, and the app returns a realistic image of them wearing the selected garment, no app download or website visit required. Designed and built the system end-to-end, from the WhatsApp messaging integration through to the try-on generation pipeline, as a self-contained product demonstrating conversational commerce for fashion/retail use cases. Key Challenges: - Frictionless UX over a messaging app: WhatsApp isn't built for structured app interactions, so the flow had to feel natural through simple image and text messages, not clunky commands. - Reliable image handling: Incoming photos vary wildly in quality, lighting, and pose, and had to be received, processed, and matched with garment images reliably. - Fast turnaround: Users expect a near-instant reply on a messaging app, so the backend had to handle image processing and model inference without long delays. - Stitching third-party services together: Twilio's WhatsApp API and Gradio's try-on model weren't built to talk to each other, so the app had to bridge them cleanly. Approach: WhatsApp integration via Twilio -Set up Twilio's WhatsApp API to receive incoming user images and send outgoing try-on results, handling the messaging layer end-to-end. Flask backend as the orchestration layer -Built a Flask application to receive Twilio webhooks, manage the request flow, and coordinate between incoming user images and the try-on model. Virtual try-on generation with Gradio - Integrated Gradio's virtual try-on model to generate the final garment-on-user image, returning a realistic composite result. End-to-end flow design - Connected the pieces so a user's WhatsApp message triggers the full pipeline automatically: receive image → process → generate try-on → send result back, all within a single conversation. Results & Impact - A working conversational shopping experience built entirely on a messaging app users already have open every day. - Zero-download, zero-signup try-on flow — removes the biggest friction point in getting users to try a new AI-powered feature. - A reusable integration pattern connecting Twilio, Flask, and a generative vision model, applicable to other WhatsApp-based commerce or personalization tools. Provided Services & Solutions 📌 Conversational App Development 📌 WhatsApp API Integration (Twilio) 📌 Backend Development (Flask) 📌 Generative AI Integration (Gradio virtual try-on model) 📌 Third-Party API Orchestration Tech Stack: Python · Flask · Twilio WhatsApp API · Gradio If you want an AI-powered experience built directly into a channel your customers already use, like WhatsApp, let's talk.

1

52

Founding engineer who ships production AI, fintech, and Web3

New to Contra

Founding engineer who ships production AI, fintech, and Web3

Cover image for JeeSankalp — (https://jeesankalp.live) IIT JEE

JeeSankalp — (https://jeesankalp.live) IIT JEE EdTech Platform Built the complete platform for JeeSankalp, an IIT JEE prep initiative by educator Sankalp Jauhari. Delivered a full product spanning a marketing site (Framer), a web app with courses, test series, free study material, and mentorship booking — plus a mobile app on the Play Store. The platform serves students across India with integrated test analysis, mock test training, and one-on-one guidance. Crossed 100,000+ submissions on the assessment platform post-launch.

0

19

Cover image for DreamXec Student Crowdfunding Platform Launch

DreamXec Student Crowdfunding Platform Launch

1

3

Cover image for Schmooze Media — Tech Lead,

Schmooze Media — Tech Lead, MarTech Agency Served as Tech Lead at Schmooze Media, a full-stack growth agency helping startups go from zero to scalable traction. Led development across SaaS builds, Shopify/Webflow projects, AI agent development, API integrations, and MarTech automation pipelines. Built and shipped multiple client products including TravelXec (1,000+ bookings), SpaceXec (custom blockchain property tokenization with live mainnet), and JeeSankalp (100,000+ assessment submissions) — all while managing a freelance-to-full-time engineering team. Grew from freelancer during college to full-time Tech Lead, owning the entire technical delivery end-to-end.

0

16

Cover image for TravelXec — (https://travelxec.com) Travel Booking

TravelXec — (https://travelxec.com) Travel Booking Platform Built a full-stack travel booking platform from scratch at Schmooze Media, later integrated into the DreamXec ecosystem. Delivered 1,000+ bookings post-launch with zero third-party booking SaaS — everything custom built. Handled end-to-end: backend APIs, booking flow, payment integration, and deployment on AWS. Architected for scale from day one with Redis caching and a Node.js/PostgreSQL core.

0

25

AI/ML engineer building production RAG & LLM agent systems —

New to Contra

AI/ML engineer building production RAG & LLM agent systems —

Cover image for Title: NEXUS AI — M&A

Title: NEXUS AI — M&A Intelligence Platform Description: Enterprise platform combining RAG, Neo4j knowledge graphs, and XGBoost ESG forecasting under a LangGraph agent. Built for PE due diligence. Image: same NEXUS AI screenshot from Upwork Link: private demo only

0

20

Cover image for Title: ASPIRE — Automated ESG

Title: ASPIRE — Automated ESG Report Generator (GRI/TCFD) Description: Built a GenAI system that converts raw ESG CSV data into a fully structured GRI/TCFD-aligned sustainability report in ~30 seconds using LLaMA 3.3. The validation layer cross-checks every LLM-generated number against source data before it reaches the report, preventing hallucinated figures in a compliance document. Includes red-flag triggers for fatalities, data breaches, and high turnover that auto-apply GRI materiality language. 57/57 tests passing, deployed on Render, Streamlit Cloud, and AWS EC2.

0

30

Cover image for Title: LEXINTEL — Autonomous M&A

Title: LEXINTEL — Autonomous M&A Due Diligence Accelerator Description:Built a 4-pass autonomous AI pipeline that ingests an entire M&A data room — PDFs, contracts, exhibits — and produces a structured legal report in under 2 minutes. Detects missing exhibits, extracts clauses across 9 legal categories, and catches cross-document contradictions like mismatched equity percentages automatically. Zero data retention, fully ephemeral processing. 0% failure rate in testing. Built with Groq LLaMA 3.3, FastAPI, Streamlit, deployed on AWS EC2.

0

33

Cover image for Title: NEXUS AI — M&A

Title: NEXUS AI — M&A Intelligence Platform Description: Enterprise platform combining RAG, Neo4j knowledge graphs, and XGBoost ESG forecasting under a LangGraph agent. Built for PE due diligence. Image: same NEXUS AI screenshot from Upwork Link: private demo only

0

40

Experienced Cloud Architect specializing in AWS, Azure, and

Experienced Cloud Architect specializing in AWS, Azure, and

Cover image for End-to-End CI/CD Pipeline and EKS Deployment with Terraform

End-to-End CI/CD Pipeline and EKS Deployment with Terraform

0

11

Cover image for Setup Datalake Solution for a bigdata client

Setup Datalake Solution for a bigdata client

0

5

Cover image for Setup Azure Solutions for Sony India

Setup Azure Solutions for Sony India

0

6

Placeholder project card media

View more →