Vetted Retrieval-Augmented Generation Professionals

“At ReferU.AI, designed and deployed an agentic RAG pipeline that automates multi-jurisdiction legal document drafting, emphasizing hallucination reduction through hybrid retrieval, validation agents, guardrails, and iterative regeneration. Experienced with orchestration frameworks (especially CrewAI) and rigorous testing/evaluation practices including human-in-the-loop review, adversarial testing, and production metrics/logging.”

“Developed and productionized VL-Mate, a vision-language, LLM-powered assistant aimed at helping visually impaired users understand their surroundings and query internal knowledge. Emphasizes reliability and safety via confidence thresholds, uncertainty-aware fallbacks, hallucination grounding checks, and rigorous offline + user-in-the-loop evaluation, with experience orchestrating multi-step LLM pipelines (LangChain-style and custom Python async) and deploying on containerized infrastructure.”

“Robotics/ML engineer who benchmarks and adapts open-source robot action models, building synthetic datasets in Isaac Sim and modifying vendor code to scale training across multiple GPUs. Also built a production-style computer vision pipeline at Zortag—training a tiny YOLO-based classifier for fake-vs-real label detection and deploying it in a real-time iOS app with additional display/spoof detection.”

“Built and deployed a production AI invention/patent review platform that compares invention submissions against patent rules to provide instant feedback, reportedly cutting legal team review time by ~80%. Learned Snowflake Cortex LLMs and production deployment (Docker + AWS) on the job, and validated system quality through human-in-the-loop testing with experienced legal stakeholders.”

“Built and deployed a production LLM/RAG intelligent document understanding platform for healthcare clinical documents (notes, discharge summaries, diagnostic reports), integrating spaCy entity extraction, Pinecone vector search, and a Spring Boot API on AWS with monitoring and guardrails. Demonstrates strong MLOps/orchestration (LangChain, Airflow, Kubeflow/Kubernetes) and a metrics-driven evaluation approach, and partnered with a healthcare operations manager to cut manual review time by 80%.”

“Healthcare-focused ML/LLM engineer who built a production hybrid RAG workflow to automate prior authorization by retrieving from medical guidelines/historical cases (FAISS) and generating grounded rationales for clinicians. Strong in operationalizing ML with Airflow/Kubeflow/MLflow on SageMaker, optimizing latency (ONNX/quantization/async), and reducing hallucinations via evidence-only prompting; also partnered closely with clinical ops to deploy a readmission prediction tool used in daily rounds.”

“Built a contract and customer documentation retrieval solution for Urban Studio, designing a RAG + Elasticsearch hybrid search stack (RRF + cross-encoder reranking) with a strong emphasis on chunking/data quality and hallucination reduction. Experienced in diagnosing LLM workflow issues via observability traces and tailoring technical demos to developer concerns like reliability and high concurrency.”

“Backend engineer who evolved Coca-Cola bottlers' Trade Promotion Optimization platform at Coke One North America, building domain-focused microservices in Node.js and Python (Flask/FastAPI) with PostgreSQL. Experienced in multi-tenant security (OAuth2/JWT, RBAC, row-level scoping by bottler/region), API contract/versioning discipline, and Azure DevOps-driven incremental rollouts with strong observability.”

“Built core perception and decision layers for a 3D AI-powered interactive avatar/agent with a robotics-like perception–reasoning–action loop, combining computer vision, NLP, and real-time response. Focused on making multimodal inputs robust (normalization, intent + emotion signal fusion) and improving real-time performance via instrumentation, profiling, and parallelization; also designed distributed, loosely coupled state-based communication and deployed services with Docker.”

“Backend/ML engineer focused on clinical AI transparency who built ShifaMind, an explainability-enforced clinical ML system using UMLS/MIMIC-IV/PubMed data with RAG, GraphSAGE, and cross-attention. Demonstrated strong production engineering via FastAPI API design and safe migrations (feature flags/shadow inference), plus HIPAA-aligned auth/RLS patterns; also delivered a real-time comet detection system reaching 97.7% accuracy.”

“LLM engineer who built and deployed an emotionally intelligent AAC communication system using an emotion-aware RAG pipeline (Empathetic Dialogues + GoEmotions) and a PEFT-adapted model. Experienced with LangChain/LangGraph and custom Python orchestration, focusing on reliability (guards, schema validation, fallbacks), latency optimization, and rigorous evaluation (automatic metrics + human-in-the-loop), with a reported 18% user satisfaction improvement.”

“Backend engineer with legal-tech and AI workflow experience: built JurisAI, an end-to-end legal research system using OCR + embeddings + Pinecone vector search to deliver citation-grounded LLM answers with safe failure modes (~90% recall@K). Also led a GW Law metadata migration into Caspio with batch validation and parallel rollout, and has strong FastAPI/GCP production reliability and observability practices.”

“Built and deployed production NLP/LLM systems including a multilingual (5-language) health misinformation detection pipeline with latency optimization (batching/quantization/caching) and explainability (gradient-based attention visualizations). Experienced orchestrating end-to-end AI workflows with Airflow and Prefect, and partnering with customer support ops to deliver an AI agent for ticket summarization and priority classification with clear, measurable acceptance criteria.”

“Full-stack engineer who built an AI-based inventory/procurement query system at Botlily/Botlerly using Flask and Google Sheets as a live knowledge base, overcoming Sheets latency with caching and structured in-memory models. Demonstrated strong LLM product engineering (40% accuracy improvement via preprocessing/prompting) and customer-driven iteration with bar/restaurant owners, evolving the tool into a more comprehensive inventory management and forecasting solution.”

“At Trellis, built and shipped a production multi-agent, authenticated GenAI chatbot for sensitive financial account inquiries (loan/payment lookups), using dynamic model routing to control latency and cost while improving accuracy. Implemented prompt-injection defenses (Meta Prompt Guard), RAG with LangChain, and LLM-as-a-judge evaluation; the system cut manual support call volume by 40%+ and was refined through close collaboration with QA-driven user testing.”

“Built and deployed a production GenAI resume screening and matching system for Florida Atlantic University, focused on improving recruiter efficiency and search relevance. Demonstrates strong RAG engineering (embeddings, query rewriting, metadata filtering, threshold tuning) plus practical reliability work (grounding constraints, fallbacks, and evaluation using real user queries) using Python REST APIs and orchestration frameworks like LangChain and LlamaIndex.”

“Full-stack engineer currently building an employee management system end-to-end with React, Node/Express, and PostgreSQL, including JWT auth and RBAC. Previously worked at TCS on large-scale State Bank of India web applications, applying Redis caching, server-side pagination/filtering, and async job offloading to improve performance and reliability.”

“At Provenbase, built and shipped a production LLM-powered semantic search and candidate matching platform (RAG with GPT-4/Gemini, multi-agent orchestration, Elasticsearch vector search) to scale sourcing across 10M+ candidate records and 1000+ data sources. Drove sub-second performance, cut LLM spend 30% with routing/caching, and improved recruiting outcomes (+45% sourcing accuracy; +38% visibility of underrepresented talent) through bias-aware ranking and tight collaboration with recruiting stakeholders.”

“Built and productionized a RAG-based semantic search system for video-derived data, focusing on measurable success metrics (p95 latency, reliability, cost/request) and strong observability (prompt versions, retrieved docs, tool calls, token usage). Experienced in diagnosing real-time issues in LLM/agentic workflows and in supporting go-to-market efforts through tailored technical demos, rapid POCs, and post-close onboarding.”

“Built and productionized a domain-specific LLM-powered RAG knowledge assistant at JerseyStem for answering questions over large internal document corpora, owning the full stack from FAISS retrieval and LoRA/QLoRA fine-tuning to AWS autoscaling GPU deployment. Drove measurable gains (28% accuracy lift, 25% latency reduction) and improved reliability through hybrid retrieval, grounded decoding, preference-model reranking, and Airflow-orchestrated pipelines (35% faster runtime), while partnering closely with non-technical stakeholders to define success metrics and ensure adoption.”

“Junior web developer turned applied AI builder who has shipped both user-facing web UX improvements (Vue.js + Drupal/Twig) and production LLM systems. Built a Google Cloud-hosted Llama/Ollama RAG customer-service chatbot with citation-based guardrails and a metrics-driven eval loop, and also delivered a large-scale Python pipeline analyzing 14M Amazon consumer reviews for flavor-trend detection.”

“Built and owned a production RAG search/Q&A platform at Data Integrity First for a client with a large, hard-to-search document library, deployed on AWS. Drove major adoption gains by adding source attribution (users trusted answers more) and improved system performance with guardrails, logging, and iterative chunking/OCR normalization—cutting fallback rate from ~22% to under 10%.”

“Built and showcased a self-made "Scholar AI" education web app that answers student queries and uses a RAG pipeline to ingest PDFs and generate MCQs for exam prep. Also delivered an AI solution for generating ad creatives and ad copy from keywords, emphasizing clear communication with non-technical stakeholders.”