Vetted Retrieval-Augmented Generation (RAG) Professionals

“Lead Data Scientist (10+ years) with recent work in healthcare data: built production pipelines that unify EHR, genomics, and clinical notes using NLP (spaCy/BERT/BioBERT) and scalable Spark-based processing. Also led development of domain-specific LLM/NLP systems for chatbots and semantic search, deploying models via FastAPI/Flask and improving retrieval with FAISS-backed, fine-tuned clinical embeddings and RAG-style workflows.”

“LLM/document AI engineer who owned a production-grade contract extraction pipeline at CORAMA.AI, ingesting PDFs and dynamic JavaScript sites from 1,000+ government sources. Built a hybrid deterministic+LLM system with two-phase prompting, Pydantic guardrails, confidence scoring, and human-in-the-loop review—cutting error rates from ~35% to <5% and processing 50k+ documents at ~95% accuracy. Also built clinician-in-the-loop orchestration in research, reducing manual labeling time from 3–4 hours to ~50 minutes.”

“ML/NLP engineer focused on production GenAI and data linking systems: built a large-scale RAG pipeline over millions of support docs using LangChain/Pinecone and added a LangGraph-based validation layer to cut hallucinations ~40%. Also built scalable PySpark entity resolution (95%+ accuracy) and fine-tuned Sentence-BERT embeddings with contrastive learning for ~30% relevance lift, with strong CI/CD and observability practices (OpenTelemetry, Prometheus/Grafana).”

“Built a production LLM/RAG-based “model excellence scoring” system at Uber to automatically evaluate hundreds of ML models, standardizing quality assessment and cutting evaluation time from days to minutes on GCP. Also delivered an NLP document classification solution for insurance claims at Globe Life, partnering closely with compliance/operations and improving routing accuracy from ~85% manual to 93% with the model.”

“Robotics/ML engineer who implemented TD3 and PPO in PyTorch to solve the challenging OpenAI Gymnasium humanoid-v5 MuJoCo task, including custom networks, rollout logic, and training scripts. Also has hands-on robotics coursework experience with ROS-based RRT motion planning on a real robotic arm, plus practical CI/CD and containerization experience (Docker, Jenkins, GitHub Actions). Currently exploring world models (VAE + sequence generator) using Euro Truck Simulator data.”

“Internship experience building a production LLM-powered podcast operations agent that automated lead intake (HubSpot), guest research, scheduling (Calendly), meeting-summary evaluation (Gemini), and human approval via Slack bot—while retaining rejected candidates for future outreach. Also contributed to ideation of a multi-agent orchestration framework with parsing and task routing, and emphasized reliability via structured prompts, HITL feedback, and prompt-based test sets.”

“Built a production LLM-powered analyst assistant at Discern Security to speed up SOC investigations using a RAG pipeline over security vendor documentation (Python PDF ingestion, vector search). Demonstrates deep, security-critical LLM engineering: structure-aware chunking with custom table parsing, grounded/cited responses, prompt-injection defenses, and post-generation validation, validated via golden datasets and adversarial testing; tool is used daily by analysts.”

“Built and deployed a production healthcare medical review agent that automates call-transcript summarization and medication reconciliation using a hybrid deterministic + LangGraph-orchestrated LLM workflow. Demonstrates strong reliability engineering (guardrails, schema validation, confidence thresholds, golden/adversarial eval, Langfuse monitoring) in a regulated environment, delivering 60% lower latency and 70%+ efficiency gains while partnering closely with care managers and operations.”

“AI/LLM engineer at Capital One who deployed a production RAG-powered fraud analysis and document intelligence platform using LangChain, OpenAI, Pinecone, Kafka, and AWS. Focused on reliability in real-time investigations via hybrid retrieval, schema-validated outputs, and LLM verification loops, reporting review-time reduction from hours to minutes and ~99% fraud detection precision.”

“ML/LLM practitioner with production experience building a healthcare review sentiment pipeline (RateMDs) using Hugging Face Transformers plus a LangChain+FAISS RAG layer for interactive querying. Also led orchestration-driven optimization of Nike’s Fusion ETL pipeline, improving runtime efficiency by 20%, and has experience translating ML outputs into Tableau dashboards for non-technical healthcare stakeholders (e.g., readmission risk).”

“ML/AI engineer with production experience at Shopify and Intel, building a deep learning product ranking system that lifted add-to-cart ~14% and serving real-time similarity search via FAISS+Redis under <20ms latency at massive scale. Also deployed computer vision models to 100+ retail edge locations using Docker/Ansible/k3s with zero-downtime rollouts, and applies strong MLOps practices (A/B testing, canary/shadow, observability) plus performance optimization (OpenVINO, INT8).”

“Engineering player-coach who recently shipped an agent-based workflow to extract key info from unstructured web data (browser agents + CDP) and populate daily digests/calendars, owning architecture through testing. Also built a Flask-based LLM evaluation and regression testing system using G-Eval/Confident AI dashboards, and applies a rigorous, research-driven approach to selecting third-party tools with stakeholder buy-in; has healthcare ops/onboarding workflow experience at Vivio Health.”

“Enterprise Customer Success professional focused on AI-driven healthcare revenue cycle automation, owning multi-clinic accounts end-to-end from onboarding through adoption, optimization, and expansion. Demonstrated measurable operational impact (cutting per-claim processing time from ~15–20 minutes to ~3–5) and strong cross-functional leadership across Product/Engineering/Sales and customer IT/ops to resolve integrations and drive sustained usage.”

“New graduate with hands-on LLM work building a RAG pipeline (HNSW, lexical reranking/boosting, ReAct) and optimizing it through ablation to dramatically reduce latency. Also building a modular personal assistant with a custom wake word model, router-driven agent selection, and integrations like Spotify with secrets managed via .env.”

“Full-stack engineer with hands-on ownership of a customer-facing advanced performance metrics experience in the Amazon S3 console, spanning React UI, Python/Node services, Redshift/RDS data access, and AWS IaC/CI-CD with CloudWatch/Route53 operational readiness. Demonstrates strong production instincts around resilience (partial failures, multi-region inconsistencies), progressive rollouts/feature flags, and reliable ETL/integration patterns (idempotency, backfills, reconciliation).”

“Built and deployed a production multi-agent RAG system at JPMorgan Chase to automate regulated credit analysis and compliance clause discovery across large internal policy/document libraries. Implemented LangGraph-based supervisor orchestration with structured state management (Azure OpenAI) to support long-running, resumable workflows, plus hybrid retrieval + re-ranking and guardrails for reliability. Strong at evaluation/observability (trace logging, LLM-judge, HITL) and at communicating results to non-technical stakeholders via Power BI embeds and Streamlit prototypes.”

“Built and shipped a production LLM-powered multi-agent RAG system to automate complex internal support workflows, integrating tool execution (SQL/APIs) with validation guardrails to reduce hallucinations. Optimized for real-world latency and cost via model routing, caching, and async parallel tool calls, and enforced reliability with CI-gated golden test sets derived from anonymized production queries.”

“Built a production LLM-powered RAG agent for healthcare/insurance operations that retrieves and summarizes patient medical documents with grounded citations, scaling to ~4.5M records. Addressed medical shorthand and terminology by fine-tuning ~120 lightweight DistilBERT models by specialty and validating entities against SNOMED/RxNorm, while using SHAP/LIME and human-in-the-loop review to make decisions explainable to stakeholders.”

“Full-stack AI/LLM engineer who has deployed a production LLM backend (Mistral 14B) on GKE to auto-transform datasets and generate runnable ML training pipelines, addressing hallucinations, schema mismatch, latency, and burst scaling with caching/prompt compression and HPA. Also has internship experience (Splunk, BlackOffer) delivering data automation and 10+ Power BI dashboards for non-technical stakeholders with measurable efficiency gains.”

“Built and owned an end-to-end AI-driven decisioning platform at Uber, combining LLM orchestration with typed tool contracts and a Snowflake-based RAG pipeline to make decisions fully auditable. Delivered large-scale measurable impact (120k requests/day, 18k cases auto-resolved/month) while improving ops SLA from 3 days to 6 hours and cutting incident response time nearly in half. Previously led a high-risk strangler-fig modernization of a legacy insurance platform across 120+ microsites at Accenture, coordinating across multiple squads with feature-flagged parallel cutovers.”