Vetted Retrieval-Augmented Generation Professionals

“Built a production LLM-powered clinical note summarization and retrieval system that structures patient/provider/payer discussions into standardized outputs (symptoms, treatments, clinical codes, and prior-auth decisions) and stores notes as embeddings for hybrid search and proactive prior-authorization prediction. Experienced with LangChain/LangGraph orchestration, RAG, and grounding against medical code databases, and has communicated model feasibility/limitations to business stakeholders (Virtusa/Comcast).”

“Backend/LLM engineer who ships production internal tooling end-to-end: automated data-request processing with monitoring-driven improvements (better error diagnostics and lower latency via query/index tuning). Also built a RAG-based internal Q&A system over company docs and operational logs with guardrails (similarity thresholds, fallbacks, response limits) and an eval loop using real user queries and human review to drive prompt/retrieval changes.”

“ML/NLP engineer focused on large-scale data linking for e-commerce-style catalogs and customer records, combining transformer embeddings (BERT/Sentence-BERT), NER, and FAISS-based vector search. Has delivered measurable lifts (e.g., +30% matching accuracy, Precision@10 62%→84%) and built production-grade, scalable pipelines in Airflow/PySpark with strong data quality and schema-drift handling.”

“AI/LLM practitioner who has deployed production chatbots across e-commerce, HRMS, and real estate, focusing on retrieval-first workflows for factual tasks like product and property search. Optimized intent understanding and significantly improved latency by using lightweight embeddings and tuning the inference pipeline on Groq (Llama 3.3), while applying modular orchestration and measurable production evaluation.”

“Full-stack engineer who built a live-streaming edtech platform at KratosIQ, owning the entire frontend and the backend streaming layer. Notably migrated the system from a P2P mesh to an SFU architecture to handle scaling under heavy load, and delivered measurable React performance gains (450ms to 40ms render time) validated via Lighthouse and web vitals.”

“LLM/agentic systems builder who has deployed production solutions for a resource management firm, using an MCP-driven architecture with Neo4j + Elasticsearch and a ChatGPT frontend to generate candidate/company “SmartPacks” and answer entity Q&A. Also built a LangGraph/LangSmith-orchestrated multi-agent workflow that automates data-infra change requests end-to-end (impact analysis, SQL + tests, and PR creation), and delivered a ~60% latency reduction through TTL-based context caching while improving accuracy via a business data dictionary.”

“Built and deployed a production, multi-tenant modular agentic AI platform at Easybee AI, using LangChain/LangGraph with Redis-backed durable state to make agents reusable, traceable, and auditable. Emphasizes reliability via strict tool schemas, deterministic controllers, tenant-level policy enforcement, and regression testing derived from real production failures; also delivered AI automation for legal/finance workflows (attorney draw and expense automation) with explainable, deterministic payouts.”

“Backend/AI engineer who has built and operated production Node.js/Express services on AWS (Postgres/Redis) and has hands-on experience shipping an AI-powered support agent using RAG (Pinecone + LLM) with grounding checks and evaluation for hallucination rate. Demonstrates strong production reliability/performance debugging, including reducing peak latency from ~2s back to sub-300ms through query and caching optimizations, plus designing agent workflows with retries and human-in-the-loop escalation.”