Production ML systems, LLM fine-tuning, RAG architectures, and agentic workflows.
tip - click ↻ metrics to flip a card and see live benchmark charts + GitHub stats
01
Qwen Data Science Instruct – QLoRA Fine-Tuned LLM
Fine-tuned version of Qwen2.5-3B-Instruct optimized for Data Science and ML coding tasks using QLoRA on 16.4K instruct examples with Unsloth. Achieved an 86% win rate over the base model with +109.5% BLEU and +66.9% ROUGE-L score gains.
Production RAG – Evidence-Grounded Modular Architecture
Recall@5 Score
90%
MRR Score
85%
Citation Accuracy
95%
Abstention Accuracy
95%
32/32Pytest Suite100% test pass rate
16+Document FormatsPDF, DOCX, Code, OCR
95.0%Citation Accuracybidirectional verified
15msFast Path Latencydynamic query router
03
ResumeDojo – AI Resume Intelligence & ATS Evaluation Engine
AI-powered resume intelligence platform and analysis engine. Evaluates resumes with zero fluff, extracts structured factual profiles via Docling and PyMuPDF, identifies ATS vulnerabilities, critiques bullet points, and benchmarks candidates against 12+ tech roles and job descriptions.
ResumeDojo – AI Resume Intelligence & ATS Evaluation Engine
Profile Extraction Accuracy
96%
ATS Scoring Consistency
94%
Bullet Rewrite Impact
91%
Schema Parser Reliability
100%
12+Canonical Rolespre-configured profiles
8Analysis ModulesATS, Bullets, JD, etc.
100%Schema Reliabilityfail-safe Pydantic repair
< 2sInference Latencycached profile reuse
04
ORCHESTRA – Multi-Agent Hackathon Judge
AI-powered hackathon judging platform. Upload a CSV of team submissions and a multi-agent pipeline — five parallel judge agents, a bias auditor, and a chief judge — scores every project automatically, generates written feedback, and produces a ranked leaderboard.
Node.jsGPT-4oMulti-AgentAgentic AINext.jsPostgreSQLNeon DB5 AI JudgesGPT-4oParallel EvalConfidence Tiers
Production-oriented Retrieval-Augmented Generation system for research papers and technical docs. Combines hybrid retrieval (Dense + BM25 + RRF), cross-encoder reranking, evidence gating, and claim-level citation verification to minimize hallucination.
Production-grade FastAPI & AI Command Portal for Tata Power DDL that transforms raw smart meter signals into a probability-ranked enforcement hit-list for targeted electricity theft raids.
Full-stack app that analyzes sentiment of YouTube video comments using a custom-trained LightGBM model exposed via FastAPI, paired with a Chrome Extension for on-the-fly analysis directly from the browser.
ML-based college prediction system analyzing JoSAA counselling data (2021–2025) with XGBoost rank prediction and chance estimation (Safe/Moderate/Risky).
Centralized multi-page web dashboard showcasing a compilation of comprehensive data analysis reports (India Crime, CPI Inflation, Delhi Rainfall) with interactive Chart.js analytics and role-based controls.