Freelance AI Developers in West BengalFreelance AI Developers in West Bengal
ProjectsPeople
Sandeep Sharma's avatar
Sandeep Sharma
proSiliguri, India
I build MVPs in 2-4 weeks |Shipped 50+ MVPs for 30+ clients
43x
Hired
4.8
Rating
83
Followers
REPLIT_EXPERT

Expert

I build MVPs in 2-4 weeks |Shipped 50+ MVPs for 30+ clients
Cover image for SmartCoach365 — AI Coaching That Feels Human
SmartCoach365 — AI Coaching That Feels Human
1
9
Cover image for SaaS AI - Contract Analysis & Legal Clarity Platform
SaaS AI - Contract Analysis & Legal Clarity Platform
1
32
Cover image for Parenthour — Full Product Build (Web + Android + iOS)
Parenthour — Full Product Build (Web + Android + iOS)
1
31
Cover image for AI-Powered Mindset & Manifestation iOS & Android App
AI-Powered Mindset & Manifestation iOS & Android App
1
18
AI Developer(2)
Eajaj Hossain's avatar
Eajaj Hossain
Kolkata, India
AI Developer & AI Agent Engineer
New to Contra
AI Developer & AI Agent Engineer
Cover image for DocFlow AI – Intelligent Document
DocFlow AI – Intelligent Document Processing Platform DocFlow AI is an enterprise document intelligence platform that transforms unstructured documents into searchable, actionable knowledge. The platform automatically extracts information from PDFs, Word files, invoices, contracts, and reports, builds a searchable knowledge base, and enables users to interact with their documents through an AI assistant using Retrieval-Augmented Generation. It combines OCR, structured extraction, RAG, AI agents, and workflow automation to simplify document-heavy business operations. Features: PDF Processing OCR Pipeline RAG AI Chat with Documents Entity Extraction Document Classification Knowledge Base Citation Generation Role-based Access FastAPI Backend Tech Stack: Python FastAPI LangGraph LangChain ChromaDB PostgreSQL Docker Redis OpenAI OCR
0
37
Cover image for Scopio – Multi-Agent AI Sales
Scopio – Multi-Agent AI Sales Automation Platform Scopio is a production-ready multi-agent AI platform designed to automate B2B sales and lead generation. The platform coordinates multiple AI agents to perform end-to-end sales workflows: Discover potential businesses from multiple sources Research company websites and public information Analyze business context using LLMs Generate personalized outreach emails Manage follow-up workflows automatically Maintain conversation history and workflow state I designed the agent architecture using LangGraph, enabling planning, tool calling, memory, and multi-step execution while integrating external APIs and backend services for reliable automation. Key Features Multi-Agent Architecture Autonomous Business Research AI-Powered Personalized Outreach Tool Calling & API Integration Workflow Orchestration Long-Term Memory PostgreSQL & Redis Integration Dockerized Deployment FastAPI Backend Tech Stack Python • LangGraph • LangChain • FastAPI • PostgreSQL • Redis • Docker • OpenAI • MCP • REST APIs
0
42
Cover image for I designed and developed a
I designed and developed a cinematic 3D interactive website concept created to turn a couple’s memories into an immersive digital experience. Instead of presenting photos in a traditional gallery, the experience transforms them into a visual journey — combining 2.5D photo depth, floating memories, particle effects, constellation-style visuals, animated transitions, ambient sound, and a cinematic storytelling flow. What I built • Premium cinematic UI/UX • Interactive 3D / 2.5D photo experiences • Depth-based photo animations • Particle and floating-memory effects • Animated timeline and counters • Interactive storytelling sections • Ambient audio experience • Responsive design • Performance-conscious Three.js implementation • Next.js-based architecture The concept A couple can turn their favorite moments — trips, dates, proposals, weddings, anniversaries, and everyday memories — into a personalized interactive experience instead of another ordinary photo album. This concept can also be adapted into a premium product for anniversaries, weddings, proposals, Valentine's Day, birthdays, and special occasions. Tech Stack Next.js • React • TypeScript • Three.js • WebGL • CSS I'm available to build similar premium interactive websites, 3D experiences, landing pages, and personalized digital experiences for brands, businesses, creators, and special occasions. #WebDevelopment #WebDesign #ThreeJS #3DWeb #InteractiveWeb #CreativeDevelopment #3DWebsite #ImmersiveWeb #CinematicWeb #MotionDesign #NextJS #ReactJS #WebGL #CreativeCoding #DigitalExperience
0
26
Cover image for Designed and developed a modern
Designed and developed a modern 3D interactive website concept for Freej Swaeleh, a Kuwaiti restaurant brand. The goal was to create a premium digital experience that combines Kuwaiti cultural identity with modern 3D web design, while making it easy for customers to explore the restaurant, menu, branches, gallery, FAQs, and ordering options. What I built • Interactive 3D website experience • Modern responsive UI/UX • Restaurant menu & dish showcase • Branch/location section • Food gallery • FAQ section • Online ordering concept • Mobile-responsive experience • Smooth animations and interactive elements AI Integration Concept I also designed the concept for an AI Restaurant Agent that could be integrated into the website to provide 24/7 customer assistance — answering menu questions, recommending dishes, providing branch information, helping with reservations/orders, and more. Live Demo: https://eajajhossain.github.io/freej-swaeleh/ Note: This is an independent concept/prototype created to demonstrate the potential digital experience and is not an official Freej Swaeleh website.
0
31
AI Developer(2)
Subham paul's avatar
Subham paul
Kolkata, India
AI Engineer
AI Engineer
Cover image for KTech is a modern online tech education platform built to he...
KTech is a modern online tech education platform built to help students and professionals gain real-world, job-ready skills. It offers industry-aligned courses in Full Stack Development, AI & Machine Learning, Data Analytics, Cloud, DevOps, Cybersecurity, and emerging technologies. Designed with a powerful MERN-stack backend, KTech focuses on hands-on learning, live & recorded sessions, secure payments, and scalable course management—bridging the gap between theory and practical industry experience.
1
69
Cover image for indiacampus.in (http://indiacampus.in) is a next-gen Learnin...
indiacampus.in (http://indiacampus.in) is a next-gen Learning Management System (LMS) designed to empower schools, colleges, and training institutes in India with a seamless digital education experience. Built for modern educators and learners, it brings together course management, interactive learning, performance tracking, and collaboration tools into one intuitive platform. IndiaCampus LMS transforms traditional classrooms into engaging online hubs that work across devices — making education accessible, organized, and measurable. From administrators to teachers to students, everyone gets the tools they need to teach and learn with zero friction.
1
61
Cover image for AI Code Explainer is an AI-powered SaaS platform built to he...
AI Code Explainer is an AI-powered SaaS platform built to help developers, students, and teams understand code faster and with more clarity. Reading unfamiliar or legacy code wastes hours. This tool solves that by acting like a smart senior developer that explains logic, suggests improvements, and highlights best practices in seconds. 🚀 Key Features Explain any code in plain, easy-to-understand language AI-powered debugging insights Best practices & code improvement suggestions Compare two versions of code side-by-side Supports multiple programming languages Clean, developer-first UI 💡 Business Model Free plan: Limited daily explanations Pro plan: Unlimited usage 📌 Current Status Live & publicly accessible Actively improving based on user feedback Focused on SEO-driven organic growth 🔗 Live Demo: https://kbs.institute/
2
67
Cover image for Book Roofing Appointments in Minutes
Book Roofing Appointments in Minutes with AI This demo showcases a fully responsive roofing website where homeowners can book inspections directly from their mobile devices using an AI-powered chatbot integrated with Calendly. The experience is designed to reduce response times, automate scheduling, and make it easier for roofing companies to convert website visitors into booked appointments. Features 📱 Fully responsive mobile design 🤖 AI chatbot for instant customer assistance 📅 Calendly appointment scheduling 🏠 Roofing inspection booking workflow ⚡ Fast and intuitive user experience 📧 Automated appointment confirmation 📊 CRM-ready lead capture 🔒 Secure and scalable implementation
1
1
100
AI Developer(3)
Arpan Goswami's avatar
Arpan Goswami
Kolkata, India
ML Engineer | AI Agent Dev | NLP & CV Expert
ML Engineer | AI Agent Dev | NLP & CV Expert
Cover image for Smart Document Analyzer
Smart Document Analyzer
0
7
Cover image for Sentiment Analysis for Product Reviews
Sentiment Analysis for Product Reviews
0
7
Cover image for Data Analysis and Prediction Website
Data Analysis and Prediction Website
0
4
Cover image for Real-time Intrusion Detection System
Real-time Intrusion Detection System
0
5
AI Developer(2)
Akashdeep Das's avatar
Akashdeep Das
Kolkata, India
Full stack web developer and automation expert.
$5k+
Earned
46x
Hired
5.0
Rating
25
Followers
REPLIT_EXPERT

Expert

Full stack web developer and automation expert.
Cover image for Chatterbox TTS: Real-Time Text-to-Speech Service
Chatterbox TTS: Real-Time Text-to-Speech Service
0
32
Cover image for Audio Processing API Deployment on AWS Lambda
Audio Processing API Deployment on AWS Lambda
0
70
Cover image for Real-Time AI Avatar Backend and Frontend integration Development
Real-Time AI Avatar Backend and Frontend integration Development
0
26
Placeholder project card media
View more →
AI Developer(1)
Durgesh Kumar's avatar
Durgesh Kumar
Kharagpur, India
Full-stack developer and founder building real-world product
New to Contra
Full-stack developer and founder building real-world product
Cover image for Built for the Accenture Innovation
Built for the Accenture Innovation Challenge (Round 2), this one tackles a problem most companies rolling out AI don't think about until it bites them: if you're running several different LLM-powered features at once — a customer support bot, an internal knowledge assistant, a tool inside a regulated decision workflow — each one needs a completely different level of scrutiny. A support bot can tolerate more risk and needs to respond fast; a regulated decision-support tool needs to be slow, careful, and willing to hold a response for human review rather than guess. AuRizz is a middleware layer that sits between an enterprise's LLM provider and its users and decides, per use case and in real time, whether a generated response should go through as-is, get redacted, get held for a human, or get blocked outright. What made this a genuinely hard build, not just an API wrapper: Policy-driven, not hardcoded. Every behavioral difference between use cases — which checks run, their thresholds, what happens on failure — lives in YAML config, not in application code. Switching a deployment's risk posture is a config edit, not a redeploy. Confidence as a first-class signal. Every check returns both a risk score and a confidence in that score — a high-risk-but-unsure reading routes to human review instead of auto-blocking, which is the actual fix for alert fatigue. Multi-provider by design. Works with Anthropic, OpenAI, Gemini, or Groq behind one interface, with automatic runtime fallback if a provider fails — switching providers is a one-line config change, not a rewrite. A real audit trail. Every decision is written to a hash-chained, tamper-evident log, and human overrides are appended as new records rather than edits — so the fact that the system said block and a human said allow is preserved, not erased. Built to be tested. 104 tests run the full pipeline — detectors, aggregation, decision rules, the audit chain — with no network calls or API keys required, because everything is built against interfaces, not vendor SDKs directly. I worked on this with a teammate — I focused on architecture, pipeline, backend, and we split the detector logic, policy engine, and audit system between us. Stack: Python, FastAPI, React, TypeScript, Pydantic, SQLite, multi-provider LLM integration (Anthropic/OpenAI/Gemini/Groq) Status: this is a working prototype, not a deployed product — the source is public and the full pipeline runs locally with real API calls or offline in the test suite, but it hasn't been hosted or put in front of real traffic yet. If you're building anything where AI output needs a guardrail — content moderation, compliance-sensitive automation, multi-agent systems that need oversight — this is exactly the kind of system design problem I enjoy.
0
30
Cover image for During my internship at Neosophical
During my internship at Neosophical Labs, I single-handedly built Sabse Bada Fan (https://sbf.ahoum.com/)(SBF), a live multiplayer quiz game, taking it entirely from an initial idea to a fully launched application. I designed the system to handle over thousands of people playing at the exact same time without slowing down, and I made sure the live leaderboards update instantly for everyone. To make the game accessible everywhere, I integrated Capacitor to seamlessly package the web platform into native Android and iOS mobile apps. Finally, I built an automated background system that perfectly runs our scheduled live quizzes and handles all the scoring completely on its own without any human effort.
0
38
Cover image for I built this because I
I built this because I was annoyed. I was paying monthly for a study library seat, and I still couldn't reliably tell if a seat would be free when I showed up. No way to check online, no way to book ahead just calling around or walking in and hoping. I figured if this was frustrating me, it was frustrating thousands of students across India who rent library/reading-room seats the same way. So I built Studoo (https://studoo.aithro.in/)and Padhloo (https://padhloo.aithro.in/)two connected products at Aithro (https://aithro.in/products)- Padhloo (student side): search study spaces by city/price/amenities, see a live seat map, request a specific seat for 1-12 months, and track your bookings, dues, and payments in one place. It also gamifies actually showing up — QR check-in/out, study streaks, points, badges, a leaderboard — so students stay consistent, not just book-and-forget. Studoo (owner side): the dashboard library/reading-room owners use to list their space, manage seat inventory and pricing per slot, approve or reject booking requests, chase due payments automatically, and see real analytics (occupancy, revenue, which slots to reprice). Free tier + two paid plans. You can see product demo video here - https://youtu.be/9Yex73MIYqQ?si=jfWqLxisRTM9N_28 I designed and built the full product end-to-end — the booking/approval workflow, the seat-and-slot inventory model, the QR-based geofenced attendance system, the payments/dues tracking, the subscription tiers, and the whole gamification layer (points, streaks, badges) on the student side. Where it stands: Got our first paying customer, a real library owner in Patna paying for the Growth plan, which is the moment this stopped being a side project and started being a business. Reached the Grand Finale of Empresario 2026 (IIT Kharagpur E-Cell), selected out of 3,000+ global registrations. Won the Platinum Jubilee Innovation Challenge (Deep Tech) at IIT Kharagpur's 75th anniversary event. What I'm good at, based on building this: turning a messy real-world workflow (owner approves seat → student pays offline → both sides need to trust the same numbers) into a system that's simple enough for a small business owner with no tech background to actually use — while still handling the edge cases (partial payments, overlapping slots, expiring bookings, geofenced check-ins) correctly under the hood. If you're a small business or founder who needs a web app or an AI-automation workflow built and shipped fast, not just prototyped that's exactly the kind of problem I like solving. Happy to talk about your project.
0
35
Cover image for SpeakYield - voice-first agri-commerce platform
SpeakYield - voice-first agri-commerce platform for Indian farmers This one came out of a government hackathon problem statement, but the problem itself is real and ugly: a smallholder farmer in Maharashtra selling onions knows yesterday's price at exactly one mandi, usually from the same commission agent who's also buying from them. They can't see the market 40km away, can't see what a processor or exporter would pay, and often sell right after harvest at the seasonal low because they need cash now, not because it's the best time to sell. Every step of that chain - price, buyer trust, quality grading, transport, payment - quietly leaks money out of the farmer's pocket. I built SpeakYield to close that gap, and built it voice-first because the people this is for often can't or won't use a text-heavy app. A farmer can literally say "I want to sell 12 quintals of onion, I need ₹40,000 right now" in Marathi/Hindi, and the app: Parses that into a structured request and reads it back for confirmation before anything commits - nothing moves on a guess Shows every nearby buyer's price as net-in-hand, after transport, commission, and fees - not the misleading headline mandi rate Recommends sell-now / split / hold based on the farmer's actual cash need, not just a price chart Ranks competing buyer offers by what the farmer actually banks, weighted by the buyer's payment-reliability history Runs the full deal lifecycle — offer, logistics, milestone payments, dispute filing — on one transparent, tamper-evident record What I built: the full stack — Next.js/TypeScript frontend, FastAPI backend, the voice pipeline (speech-to-text → LLM intent parsing with strict schema validation → text-to-speech read-back), the buyer-matching and net-price ranking engine, and the deal/ledger system. Solo project, ~12 commits from architecture to a working two-sided prototype (farmer view + buyer view), with CI, linting, and end-to-end tests. Stack: Next.js, TypeScript, FastAPI, Python, LLM-based voice intent parsing, PostgreSQL/Redis (production design) I like this kind of problem specifically because it's not "build a CRUD app" — it's translating a messy, high-stakes, low-trust real-world transaction into software that has to work for someone with a ₹6,000 phone and patchy network, not a power user. If you need someone who can take a genuinely fuzzy problem (multi-party trust, real-time matching, voice/AI interfaces) and turn it into a working product fast, that's exactly this.
0
43
AI Developer(1)
Abhishek Jha's avatar
Abhishek Jha
Kolkata, India
15+ Yrs Developer With Projects of AI, Blockchain, Websites
7
Followers
15+ Yrs Developer With Projects of AI, Blockchain, Websites
Cover image for FixMySlide .. created in <
FixMySlide .. created in < 24 hrs.. via Figma Make is a Text to Slides Designer created using Figma Make, and Integration with Supabase and OpenAI API.. 1. FixMySlide Figma Make Site Link: https://git-trout-05007105.figma.site 2. FixMySlide Community Link: https://www.figma.com/community/file/1649630322186671975 3. Walkthrough Video: https://youtu.be/J-GPSBo2gt8 4. Social Clip: https://x.com/EasyBasedotsite/status/2067829094625255627 I have also used 1. #FigmaMCP to create initial Deck Design then 2. #FigmaWeave to Create Background Design then 3. #FigmaMake
2
5
256
Cover image for See AI. — A flippable
See AI. — A flippable AI literacy magazine (built in Wonder) My family kept asking: "Is this message real? Is this photo AI?" So I built See AI. — a 10-spread flippable magazine for daily life. Not for developers. For anyone with a phone. 🔗 Wonder file: https://app.wonder.so/abhishek-jha/files/019f1d4f-7698-7319-b303-4591537e5739 🌐 Live preview (optional): https://see-ai-delta.vercel.app What's inside: • Cover + 8 photo spreads — scams, fake photos, voice clones, homework • Full-width sponsor ads (WhatsApp, Midjourney, NotebookLM, Truecaller, etc.) • Spine-bound page-flip interaction • Back page: advertising contact + QR + barcode Designed in Wonder using Chat (layouts) + shader (dark editorial stage). Plain words, real situations — no jargon. Walkthrough video attached. #wonderchallenge
4
3
296
Cover image for Angel Baby — Almost Angels
Angel Baby — Almost Angels Co. | Recraft Challenge Meet Angel Baby 👼 Angel Baby is the mascot of Almost Angels Co. — a fictional brand for everyday comfort. A pint-sized celestial intern who specializes in almost-invisible acts of kindness. Clumsy but devoted, Angel Baby proves magic doesn't need spectacle — just presence. 🔗 Recraft project: https://www.recraft.ai/project/08a8ca2e-5165-4e40-92fd-0558989d1501 What's included: • Original mascot — Angel Baby • Custom wordmark — Angel Baby with Almost Angels Co . • Sticker sheet + 5 product lineup (soap, sticker, doll, tea, scent) • Poster / cafe scenes + consistency proof • Brand Video in Landscape (see video) Built entirely in Recraft Studio — V4.1 Exploration, Vector wordmark, reference workflows, and image-to-video. #recraftchallenge
12
5
565
Cover image for BitEdu - ReactJs Theme For Bitcoin Education Website
BitEdu - ReactJs Theme For Bitcoin Education Website
0
9
AI Developer(1)