Ahmedabad, GujaratBuilding in public since Jan 2023 (~3.6 yrs)
I spent three years building production RAG and agentic AI systems inside enterprise teams before stepping into a founding engineer role, now owning architecture end-to-end for an AI-native ATS.
A timeline of milestones captured directly from real, verified work.
Each signal ties back to a specific, evidenced moment - not a self-rating.
Systems shipped end-to-end, from schema to deploy.
Architecture, mentorship and decisions owned solo.
Gaps closed - false positives, edge cases, dead ends.
New tools and depth picked up on the job.
What Lucky actually reaches for, pulled from the tags attached to captured moments - not a keyword list.
Case studies, not bullet points - impact numbers attached to each one.
End-to-end ATS for SME recruitment agencies with LLM-based resume parsing, semantic candidate matching, and automated pipeline management.
Intelligent SAP system with autonomous workflow execution, NL-to-SQL via Vanna AI, BGE+Qdrant retrieval. 95% forecast accuracy, 40% efficiency gain, 20% cost reduction.
ML camera-based test analysis. 25% accuracy improvement, 35% faster data processing, 5K+ tests/month at 99% uptime.
React Native field app with geotagging; 30% user adoption increase, 15% reduction in electricity distribution losses.
RAG-based smart chatbot using LLaMA 3.2 8B/vLLM, BGE + Qdrant. 95% retrieval accuracy, <800ms latency, 10K+ queries/day, 50% recruiter efficiency gain.
End-to-end parsing and ranking platform. 93% match accuracy, auto-ingested via Microsoft Graph API, Odoo sync cut screening time by 50%.
Real-time multi-entity verification with advanced matching algorithms; 60% accuracy increase, 50% faster verification.
Independent builds, open-source contributions, technical writing, and experiments beyond the day job.
A combined view of your activities across the tools that you use daily (GitHub, Medium, etc. - coming soon). Add earlier projects as a graph entry if dates available.
