Design Engineer for startups. Next.js, Supabase, Figma
Design Engineer for startups. Next.js, Supabase, Figma
Full Stack Developer | Custom CRM/ERP |Laravel | Next.js |
- 16
- Followers
Full Stack Developer | Custom CRM/ERP |Laravel | Next.js |
Backend & Web Developer | APIs, AI & Automation
New to Contra
Backend & Web Developer | APIs, AI & Automation
I built ProofFace a visual provenance & content verification engine in Rust
I have been building ProofFace an end-to-end visual provenance and content verification engine built in Rust.
The idea is simple:
Finding an image online doesn’t prove that it’s authentic, original, or unchanged.
So I built a verification pipeline that goes from:
📸 Image input
→ 🧠 Neural face detection
→ 🔎 Web visual discovery
→ 🧬 Biometric similarity
→ 🔐 Deterministic SHA-256 fingerprinting
→ ⛓️ Polygon Amoy blockchain proof
→ ✅ Verification result
Some of the things I worked on:
• ONNX-based face detection
• 128-dimensional biometric embeddings
• Presentation attack detection
• Parallel visual candidate evaluation
• Cosine similarity matching
• RFC 8785 JSON canonicalization
• SHA-256 content fingerprinting
• Polygon smart-contract integration
• Automated unit & integration testing
The project currently has 30 passing tests.
What I enjoyed most was bringing several different areas together computer vision, Rust systems programming, cryptography, and blockchain into one reproducible verification workflow.
GitHub:
https://github.com/nikhilkumarpanigrahi/proofFace
Would love to hear what you’d improve or add to a system like this.
3
372
Full-stack engineer shipping production SaaS & AI systems
New to Contra
Full-stack engineer shipping production SaaS & AI systems
GenAI Engineer | AI Agents, RAG & Trading Systems
GenAI Engineer | AI Agents, RAG & Trading Systems
🍛 Food Ordering Chatbot: order food and track deliveries just by chatting.
I built a restaurant website with an AI chatbot (Dialogflow ES) and a Python FastAPI backend. Customers can place and track orders in plain English.
What it does:
• New Order: “2 Rava Dosa and one samosa” → the bot adds the items. You can add or remove items in the same chat (“remove the samosa”).
• Completes the order, saves it to MySQL, and returns an order ID and the total bill.
• Track Order: share an order ID and get its live status (in transit or delivered).
How it works: Dialogflow detects the intent and extracts the food items and quantities. A FastAPI webhook sends each intent to its own handler and keeps a separate in-progress order for each chat session. MySQL stores the orders and their status.
Tech: Python · FastAPI · Dialogflow ES · MySQL · HTML/CSS
🔗 github.com/bns218/Food-Chatbot
0
43
🎮 Agentic Game‑Builder AI: describe a game in plain English, get a fully playable browser game.
I built a multi‑agent pipeline on Google’s Agent Development Kit (ADK) and Gemini. It turns an idea like “a retro space shooter with power‑ups and a boss fight” into a working game in one self‑contained HTML file.
How it works:
1️⃣ Clarify: a LoopAgent asks focused questions until the requirements are clear.
2️⃣ Plan: a Planning agent designs the entities, mechanics, controls and win/lose rules as a validated JSON plan.
3️⃣ Build: Generator + Writer agents produce the code. Forced tool calls and a fallback extractor make sure a playable file always comes out.
4️⃣ Play: a live dashboard (FastAPI + WebSockets) streams the code as it’s written and runs the game in a sandboxed preview.
Highlights: Canvas‑drawn graphics and Web Audio sound effects (no external assets), keyboard + mobile touch controls, and Docker support.
Tech: Python · Google ADK · Gemini · FastAPI · WebSockets · HTML5 Canvas · Docker
🔗 github.com/bns218/Agentic-Game-Builder-AI-
0
57
🤖 BTST Trading Research Agents: a multi-agent AI system for overnight stock research.
I designed four specialised AI subagents and packaged them as a Claude Code / Cowork plugin. They automate the research for BTST (buy today, sell tomorrow) trades in NSE F&O stocks.
The agents:
🌍 market-context: decides if it’s safe to hold new positions overnight (index moves, VIX, FII/DII flows, global cues, upcoming events).
📰 catalyst-analyst: finds out why each stock moved, scores its news catalyst from -2 to +2, and vetoes stocks with real event risk.
☀️ morning-briefer: an 8:30 AM pre-market brief with a buy/sell watchlist and a table showing which data was verified.
🎯 exit-manager: reads live holdings and prices through a read-only Zerodha Kite MCP connection and recommends sell or hold for each position.
Design highlights:
• Each agent gets only the tools it needs, and none of them can place orders.
• Agents return structured JSON so the next step in the workflow can use their output directly.
• Scheduled tasks run the full trading day automatically (8:30 AM, 3:05 PM, 4:15 PM).
• Built-in honesty: if a fact can’t be verified, the agent leaves it out or marks it “NOT verified” instead of making it up.
Tech: Claude Code subagents · MCP · Prompt engineering · Plugin packaging
🔗 github.com/bns218/BTST
0
51
🎙️ Live Captions + Translation: real-time speech-to-text with instant translation.
I built a Streamlit web app that listens to your microphone, shows live captions as you speak, and translates them into another language in real time.
How it works:
1️⃣ Mic stream: streamlit-webrtc captures live audio frames in the browser.
2️⃣ Speech-to-text: Kyutai’s 2.6B-parameter STT model (Hugging Face Transformers) turns the audio into English text.
3️⃣ New-word detection: only newly spoken words are sent for translation, so the app doesn’t re-translate the whole caption every time.
4️⃣ Translation: Meta’s NLLB-200 (600M) model translates into any of 200 languages. Hindi is the default.
Engineering highlights:
• Models load once and stay cached (st.cache_resource), so the app responds quickly.
• Runs on GPU in float16 when available and falls back to CPU.
• Switching the target language takes one setting change.
Use cases: meetings, lectures, accessibility for hearing-impaired users, and multilingual conversations.
Tech: Python · PyTorch · Hugging Face Transformers · Streamlit · WebRTC
🔗 github.com/bns218/live_caption_app
0
14
FULL STACK WEB DEVELOPER AND DESIGNER
Created an automated reconnaissance and asset discovery engine that integrates offensive utilities with AI-driven threat triage. Built a FastAPI backend backed by Celery and Redis to execute heavy subdomain discovery (subfinder), port scanning (httpx), and web crawling (katana) concurrently. Configured a PostgreSQL ledger to store asset records and integrated OpenAI/Ollama APIs to parse raw logs, filter out false positives, and suggest potential exploit targets. Exposes a clean REST API for configuring targets and viewing crawled subdomains.
1
48
Designed and built a consent-first GPS tracking ecosystem featuring a React Native mobile app, a Node.js backend, and a real-time web dashboard. Implemented robust background location services with a permanent Android notification bar to comply with privacy laws. Integrated an offline queue using AsyncStorage that buffers up to 2,000 coordinates during connection drops and auto-syncs via batch uploads once restored. Fingerprinted devices with stable hardware-linked IDs and displayed active paths and accuracy zones on a dark-themed Leaflet.js dashboard map.
1
73
Developed an educational cybersecurity platform and live network simulation dashboard. Engineered a FastAPI (Python) backend to safely model network attack vectors including DDoS floods, dictionary brute-forcing, and phishing intercept points. Built a responsive React + TailwindCSS dashboard displaying live packet rates, network latency spikes, and vulnerability scoring via WebSockets. Integrated automated reporting modules enabling administrators to instantly export structured incident details into printable PDF audits and Excel spreadsheets.
0
53
Designed and developed a highly interactive, futuristic corporate portal for a cybersecurity firm using React, Vite, and Tailwind CSS. Implemented a 10-years-ahead dark-mode design with smooth animations powered by Framer Motion and custom particle networks via tsparticles. Structured the app using React Router DOM and optimized SEO indexing with dynamic metadata headers via React Helmet Async. Showcases core compliance matrices, interactive service grids (Red Teaming, Blue Teaming, GRC), and product catalogs at a fluid 60 FPS.
1
68
Helping brands stand out with clean, modern web design
- 1x
- Hired
- 5.0
- Rating
- 13
- Followers
Helping brands stand out with clean, modern web design
I design products for AI startups and build them in code
- 5.0
- Rating
- 6
- Followers
I design products for AI startups and build them in code
