Résumé · Open to Forward Deployed roles
Neeraj Bhargav Rondla
Forward Deployed AI Engineer · End-to-End Gen AI Ownership · Zero-to-One Production Systems
01
Profile
The engineer you hand the ambiguous, end-to-end problem to. I run the technical discovery, decompose the problem into a shippable system, and own the whole stack — retrieval, agents, and LLM evaluation plus the streaming front-end, data layer, and infrastructure underneath. Currently the sole AI engineer at Landair Advisors, owning five production systems zero-to-one in NYC commercial real estate. Depth where the problem is hard; range where shipping demands it. One engineer, model to interface to infrastructure, zero handoffs.
02
Experience
2026 – Present
New York, NY · On-site
Applied AI Engineer — Owns 5 Production AI Systems
Landair Advisors
- 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
Nov 2025 – Jun 2026
Remote · USA
AI Software Engineer — Full Lifecycle, Zero Handoffs
Innovcentric LLC
- 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
Aug 2021 – Jul 2023
Hyderabad, India
Software Engineer — NLP, AI Tools & Full-Stack
Wipro Ltd.
- 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
03
Selected projects
NYC Agentic Underwriter & Feasibility
CRE Intelligence Platform
Built an autonomous CRE underwriting platform resolving NYC street addresses via DCP GeoSearch. Integrates parallel DoITT PLUTO & ACRIS Deed Sales queries and a Zoning RAG vector database. Features a pure CSS 3D buildable massing visualizer, interactive pro forma calculator, and a Claude-powered 'Ask the Agent' chat drawer.
React · FastAPI · Python · Claude Sonnet 4.5 · Leaflet
Open-Source MCP Server for AI Coding IDEs
VIBETTER
Built and maintained an open-source MCP server that brings deep codebase intelligence to AI coding IDEs — git-diff explanations, source-grounded Q&A with file:line citations, dependency graph visualization, and audio code walkthroughs.
Python · FastMCP 3.0 · Gemini API · Vue Flow · Watchdog
Universal State Manager & Handoff Bridge
OmniContext
Built a local daemon and global CLI tool that aggregates project Git state into a compressed Markdown prompt for web LLMs, and exposes it via a native Model Context Protocol (MCP) server for IDEs like Cursor and Claude Code.
Next.js · React · TailwindCSS · Node.js · MCP SDK
LangGraph Multi-Agent Context Orchestration Engine
Context Refinery
Built a cross-platform desktop app (Tauri v2 + Vue 3 + FastAPI) with a LangGraph multi-agent pipeline — intent analysis, hybrid retrieval (ChromaDB dense + BM25 sparse + Reciprocal Rank Fusion), cross-encoder reranking, and iterative self-refinement — with multi-provider LLM support including local models via Ollama.
Python · LangGraph · FastAPI · Vue 3 · Tauri v2
04
Capabilities
Forward-Deployed Delivery
End-to-End Gen AI Ownership · Zero-to-One Production Deployment · Technical Discovery & Scoping · Problem Decomposition · Ambiguity Navigation · Pilot → Production · Stakeholder Communication · White-Glove Onboarding · L1–L2 · Runbooks · Office Hours · Post-Deployment Optimization
LLM Systems
GPT-4 / 4o · Claude Sonnet 4.5 / Opus · Gemini (2M context) · Llama 3 / Mistral (Ollama) · Prompt Engineering · Versioning · Structured Outputs · JSON Mode · Streaming · SSE · Function / Tool Calling · SFT · LoRA / QLoRA · Token & Cost Optimization
Retrieval & RAG
LangChain · LlamaIndex · ChromaDB · Pinecone · FAISS · pgvector · Weaviate · Hybrid (BM25 + Dense + RRF) · Cross-Encoder Re-ranking · Semantic / Recursive Chunking · Agentic RAG · Document Ingestion Pipelines
Agents & Orchestration
ReAct · Plan-and-Execute · LangGraph · Multi-Agent Systems · MCP · FastMCP 3.0 · Sub-Agents · Tool Registry · Memory (buffer + vector) · Human-in-the-Loop · DSPy · asyncio · Event-Driven · Workflow State Machines
Evaluation & Observability
RAGAS · DeepEval · LangSmith · AgentOps · Arize Phoenix · LLM-as-Judge · Hallucination Detection · Faithfulness Scoring · Drift Monitoring · Safety Guardrails · Prompt Injection Defense · OpenTelemetry
Machine Learning & NLP
HuggingFace Transformers · Scikit-learn · TensorFlow · PyTorch · Text Classification · NER · Summarization · Transfer Learning · CNNs · ResNet · Grad-CAM · Pandas · NumPy · MLOps
Frontend & AI UX
React 18/19 · Next.js 16 · TypeScript · Vue.js 3 · Vue Flow · Tailwind CSS v4 · Streaming Chat UIs · Server Components · RSC · WCAG 2.1 AA · Framer Motion · Tauri v2 · Leaflet · Figma · Lighthouse
Backend & Infrastructure
Python · FastAPI · Pydantic · Node.js · NestJS · Java · GraphQL · WebSockets · PostgreSQL · Prisma · Supabase · MongoDB · Redis · Docker · Docker Compose · AWS (EC2 / S3 / Lambda / ECS) · Vercel · GitHub Actions · Nginx · Microservices · Health Checks · Structured Logging
05
Education
2023 – Dec 2025
M.S. Computer Science
New Jersey Institute of Technology (NJIT)
Machine Learning · NLP · AI Systems · Software Engineering · Capstone: AI Health Platform
2018 – 2022
B.Tech. Computer Science & Engineering
JNTUH — Hyderabad, India
Updated Jun 2026 · This résumé is an on-site page — use Print → Save as PDF for a file copy.