Hi, I’m Neeraj.

Experience

1. Applied AI Engineer — Owns 5 Production AI Systems

   2026 – Present

   Landair Advisors · New York, NY · On-site

   • Applied AI Engineer at a NYC commercial real-estate brokerage — inherited and own five production AI systems end-to-end on NYC property data (ACRIS, PLUTO, DOB, NY DOS)
   • Skiptracer — LLC-chain owner resolution via a NY DOS → ACRIS → IDI waterfall with confidence scoring; ≥95% owner + phone accuracy target. Python · Supabase · Claude Haiku
   • CompScope — Supabase database of 9,391+ comparable sales with PLUTO + ACRIS asset-type classification, powering broker deal analysis
   • BuyerScope — ranks buyers per asset type from ACRIS transfers + DOB permits into top-30 outreach lists; 2,456 scored, 109 Tier-A. Python · Supabase
   • P1 Generator — webhook MMS owner outreach: CallTools → Flask → Twilio MMS + Cloudflare R2 + SendGrid
   • Call Notes Worker — inbound-call transcription + scoring: CallTools audio → Whisper → GPT-4o → structured output. Node.js · Linode
   • ABV — agentic real-estate valuation tool on the same data stack, demoed to management and live at realestate-agentic.vercel.app

2. AI Software Engineer — Full Lifecycle, Zero Handoffs

   Nov 2025 – Jun 2026

   Innovcentric LLC · Remote · USA

   • Owned the complete Gen AI strategy and implementation lifecycle for enterprise customer-experience platforms — technical discovery with product owners and operations managers, problem decomposition from ambiguous business needs into production AI architectures, pilot validation before full rollout, and post-deployment optimization — one engineer, model to interface to infrastructure, zero handoffs
   • Built a production-grade RAG pipeline (LangChain + ChromaDB + FastAPI + Pydantic) over 10,000+ pages of support documentation — PDF/DOCX ingestion, recursive chunking (512-token windows, 50-token overlap), OpenAI embeddings, and metadata filtering — delivering sub-2s semantic search for 100+ support agents and replacing manual document lookup entirely; benchmarked 4 chunking strategies and 3 embedding models to tune retrieval
   • Deployed an autonomous ReAct agent on GPT-4 function calling with MCP-style tool-use chains — knowledge retrieval, account-context lookup, multi-step reasoning, and sub-agents for specialized tasks — running 5–10 tool calls per query with self-correction loops, dual memory (conversation buffer + vector store), and Human-in-the-Loop escalation for billing-sensitive edge cases
   • Built the eval harness that proved it worked: RAGAS (faithfulness, relevance, hallucination scoring), LangSmith observability, drift monitoring that held the line through the GPT-4 → GPT-4o migration, and prompt versioning — cutting factual errors ~60% and codifying the results as repeatable deployment artifacts
   • Engineered 50+ prompt templates (chain-of-thought, few-shot, instruction tuning) with safety guardrails, prompt-injection defense, tone alignment, and a version-controlled lifecycle — reviewed and shipped like production code, not tuned ad hoc
   • Owned the full stack with zero handoffs: a streaming chat UI (real-time token rendering, accessible, mobile-responsive) in Vue 3/React + Tailwind, a FastAPI service layer with structured error handling and Redis caching, and Docker + Nginx + GitHub Actions CI/CD — shipped to production with zero-downtime deployments across environments
   • Designed the UX in Figma (WCAG 2.1 AA, component libraries, responsive breakpoints) and validated it with real users; ran white-glove delivery — L1–L2 support, weekly office hours, and stakeholder runbooks — backed by OpenTelemetry instrumentation, structured logging, and health checks

3. Software Engineer — NLP, AI Tools & Full-Stack

   Aug 2021 – Jul 2023

   Wipro Ltd. · Hyderabad, India

   • Built and deployed an AI-powered code-review assistant (Python + OpenAI Codex) with custom prompt engineering for logic-error and code-smell detection — cutting PR merge cycles 25% and adopted by 30+ engineers
   • Designed an NLP ticket-routing pipeline (Scikit-learn + HuggingFace BERT, Pandas, NumPy) hitting 91% accuracy on 5,000+ tickets/month and reducing manual triage 40%; delivered a conversational AI chatbot with intent detection, FAQ automation, conversation memory, and escalation logic across 3 enterprise portals — 40% fewer repetitive queries for 10,000+ users
   • Built and maintained enterprise React applications at 99.5% production SLA — interactive components, form validation, Chart.js dashboards, and Lighthouse/code-splitting performance work; created a reusable component library that accelerated delivery ~30% and led a jQuery → React SPA migration for 45% faster page loads
   • Engineered event-driven REST and GraphQL services (Java + Python, PostgreSQL + SQLAlchemy + Alembic) with query optimization across tables of 5M+ records (~55% faster); trained supervised ML models (Random Forest, Logistic Regression, Gradient Boosting) with automated hyperparameter tuning and cross-validation, and resolved 200+ defects across 4 release cycles

Stack

Seven domains, end to end — the tools I reach for to take an AI problem from prototype to production.