I build the crawlers and scheduled jobs that pull data in, the tests that ensure the data is valid, and the APIs and apps that serve it.
Notes from the build — deep dives on data pipelines, applied ML, and the engineering behind shipping systems that hold up in production.
Backfilling two decades of insider-trade data from the NSE PIT API meant chunked date windows, composite-key dedup, and reconciling against a second source to close a reporting lag.
The difference between a pipeline you babysit and one you forget about is what happens on the second run. Incremental loads, adaptive backoff, and reruns that heal gaps.
From raw trade and quote ticks to minute bars to a directional model — and the leakage traps that make backtests lie if you let them.
28-pipeline NSE market-data ingestion layer feeding 12+ datasets into a partitioned store.Market Data Platform
Full-stack TypeScript app scraping a book catalog into PostgreSQL, served via Next.js with real-time WebSocket scraping.Product Explorer
Solo-built production legal-emergency platform — ~30 Express endpoints over PostgreSQL with JWT auth, a real-time Twilio call-dispatch engine, and Haversine lawyer matching, deployed on Railway and Vercel.DekhLaw Legal-Emergency PlatformProduction law-firm marketing site in Next.js 14 + TypeScript — 14 routes, Resend-backed lead capture, Zod-validated forms, and full SEO/JSON-LD, designed and shipped solo.Law Firm WebsiteAutonomous job-search bot — scrapes Indeed, Glassdoor, and LinkedIn listings, scores them against a master profile, and builds a tailored resume per match with an LLM, rendered on demand via FastAPI.Job Application Bot
Fraud-detection model on 6.4M transactions — 95% caught at 0.995 ROC-AUC despite a 0.13% fraud rate.Fraud Transaction DetectionView code Intraday price-direction system over 9.4M NSE ticks, raising next-minute precision from 0.51 to 0.61.Minute-Level Stock PredictionView code Quantified how Bitcoin Fear & Greed sentiment drives trader PnL across 211K crypto trades, with a contrarian sentiment-gated signal.Trader Sentiment AnalysisView code Semantic product-search engine that embeds descriptions and ranks by cosine similarity — finds matches with no shared keywords.Nexora Semantic Vibe MatcherView code End-to-end NLP system classifying support tickets by issue type and urgency and extracting entities, served via a Gradio app.Support Ticket ClassifierView code Semantic quote search — fine-tuned sentence embeddings + FAISS index over ~2,500 quotes, served through Streamlit.Semantic Quote RetrievalView code Multi-task CNN predicting age and gender from a face photo, trained on 10,000+ UTKFace images with face detection and alignment.Age & Gender ClassifierView code Feed-forward classifier built in pure NumPy — 97.4% accuracy / 0.995 ROC-AUC on Breast-Cancer-Wisconsin, with hand-derived backprop.Neural Network From ScratchView code From-scratch NumPy multi-task network predicting age and gender from 24,102 face images — shared trunk, two heads, manual backprop.Multi-Task Face NetworkView code Linear regression built end to end in pure NumPy — hand-derived gradient descent and a closed-form solver, validated vs scikit-learn.Linear Regression From ScratchView code Recruiters get 200+ per role. Generic gets filtered before a human looks. Your experience isn’t the problem.
The bot reads the JD and selects the exact bullets, title and skill framing that match it. Every application speaks that role’s specific language. Automatically. Every time.
Recruiters stop reading after the first 50. The window is under an hour from posting. You can’t watch three boards while that window opens and shuts.
The bot monitors Indeed, Glassdoor and LinkedIn continuously. The moment a match posts, you get a Telegram ping with the apply link and a tailored résumé ready to go. First wave, not after it.
10 roles a day is 10 tailoring sessions. You’re spending more time in Word than applying. And the rushed ones always look it.
You write your bullets once. The bot selects the right ones per role, every time. Your master profile becomes every tailored résumé you’ll ever need.
Coming soon
What’s Up On Socials
@gmail.com
Got a project or a question? Drop me a line.
Data Engineer | From crawlers to APIs
Ernakulam, Kerala, India 500+ connections Connect ↗Data pipelines, from crawlers to APIs. Ingestion, data validity, and the services on top.
- Fraud_Transaction_Detection
- minute-level-stock-prediction
- Trader_sentiment_analysis
View profile ↗Vishnu · Ex-chinmayite · UPES’25
Follow ↗Curious about data, growth & discipline — sharing experiments and insights as I figure things out.
Subscribe ↗Follow me on social media