Vetted Retrieval-Augmented Generation Professionals

“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).”

“LLM-focused customer-facing engineer who repeatedly takes document Q&A and agentic prototypes into secure, monitored production systems. Experienced in reducing hallucinations via RAG + guardrails, diagnosing retrieval/embedding issues in real time, and partnering with sales to run metrics-driven PoCs that overcome accuracy/security objections and drive adoption.”

“Backend/AI engineer who built and scaled an internal AMD semiconductor manufacturing microservice platform (SMR), reworking a synchronous lot-request workflow into an event-driven RabbitMQ/Celery/FastAPI pipeline. Diagnosed and fixed peak-load reliability issues using deep observability and Kubernetes autoscaling, cutting notification latency back to sub-second and reducing duplicates via idempotency/DLQs. Also shipped an LLM-powered natural-language search with schema-constrained JSON outputs and guardrails, plus a plan-execute-verify Jira bug-resolution agent that can propose fixes and raise PRs under restricted permissions.”

“Summer intern on AWS Lambda tooling team who shipped Finch support in AWS SAM CLI, adding OS/runtime detection and robust fallback behavior to preserve Docker compatibility across developer environments. Also built an end-to-end RAG system for querying arXiv quantitative finance papers using Postgres/pgvector with two-stage retrieval, citation-grounded prompting, and rigorous evaluation loops driven by IR metrics and user feedback.”

“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.”

“LLM/agentic workflow practitioner (Continuum AI) who productionized an LLM system for manufacturing RMA intake and warranty claims by moving from a brittle prompt to a modular pipeline with RAG, function-calling extraction, deterministic validation, and strong observability. Also diagnosed and fixed an agentic ticket-triage misrouting issue by tracing failures to retrieval timeouts, adding guardrails/fallbacks, and implementing retries plus continuous evaluation—bringing misroutes near zero while creating a repeatable debugging playbook.”

“LLM engineer who has deployed privacy-preserving, real-time workplace risk monitoring over massive enterprise chat/email streams, tackling latency, hallucinations, and extreme class imbalance with model benchmarking, RAG + fine-tuning, and a pre-filter alerting layer. Also built an agentic legal contract drafting system (Jurisagent) using LangGraph/LangChain with deterministic multi-agent control flow, structured outputs, and reliability-focused evaluation/telemetry.”

“Built and shipped a production LLM-powered investor research feature for a fintech product, focused on grounded answers and minimizing hallucinations. Implemented retrieval-quality and evidence-coverage gating with clear refusal fallbacks, and evaluates systems with regression tests and metrics like correct-refusal rate, hallucination rate, and latency. Comfortable orchestrating workflows with LangChain or custom Python depending on production needs.”

“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.”

“Built a hackathon "Patient Summary Assistant" backend focused on healthcare workflows, combining RAG-based summarization with HIPAA-minded privacy controls (NER redaction + encryption). Demonstrated strong infra skills by deploying on Kubernetes with Helm/HPA and GitOps (ArgoCD), plus migrating from OpenAI to an on-prem Llama 3 stack (vLLM, quantization, shadow-mode testing) and adding real-time Kafka ingestion for patient vitals/anomaly alerts.”

“Built and productionized a RAG-based analytics Q&A assistant for a financial analytics team, enabling natural-language querying across 200+ datasets (SQL tables, PDFs, compliance docs, wikis) and cutting turnaround time by 60%. Deep experience delivering regulated, audit-ready LLM systems on Azure (Azure OpenAI + LangChain) with strict grounding/citations, hybrid retrieval, and AKS-based low-latency deployment, plus strong collaboration with compliance analysts and auditors via iterative Gradio demos.”

“Built and deployed a production RAG-based multi-agent chatbot during an internship to help consultants answer client questions and guide users through new IT systems with step-by-step instructions. Demonstrates hands-on experience with LangGraph/LangChain/Google ADK, unstructured document parsing and chunking for RAG, and a reliability-first approach to agent workflows (metrics, fallbacks, human-in-the-loop, guardrails).”

“ML/LLM engineer building production, real-time fraud detection for financial transactions using a two-tier architecture (fast ML + GPT) to deliver both low-latency decisions and analyst-friendly risk explanations. Experienced orchestrating end-to-end retraining, drift monitoring, and automated model promotion with Databricks Jobs/Workflows and MLflow, and partnering closely with fraud analysts to tune alerts, thresholds, and dashboards.”

“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).”

“Built an "AskMyVideo" system that turns YouTube videos into queryable knowledge graphs by transcribing audio (Whisper), chunking and embedding content, and enabling traceable answers back to exact timestamps. Strong in entity resolution (rules + fuzzy matching + TF-IDF/cosine with PR-curve thresholding) and modern retrieval stacks (FAISS, hybrid dense/sparse, domain fine-tuning with ~12% precision gain), with a production mindset using Airflow/Prefect, Docker/FastAPI, and LangSmith/Prometheus/Grafana observability.”

“LLM/AI engineer with production experience building a retrieval-based document intelligence system that extracts information from PDFs/emails, backed by Python + Spark pipelines. Focused on reliability and cost/latency optimization (caching, batch processing) and has hands-on orchestration experience with Airflow (sensors, retries, alerts). Also partnered with business stakeholders to deliver customer feedback classification/summarization for faster sentiment insights.”

“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.”

“CMU candidate with hands-on experience taking LLM concepts from research prototypes toward production-ready designs (structured outputs, guardrails, failure-scenario evaluation). Also partnered with sales/customer teams at Mazecare to drive adoption with Dontia Alliance (largest dental clinic chain in Singapore) and engaged Singapore government stakeholders, bridging clinical workflow needs with IT security/integration concerns.”

“Built and deployed an on-prem, HIPAA-compliant LLM pipeline for oncology-focused clinical note generation and decision support, emphasizing grounded differential diagnosis and explainable reasoning via RAG to reduce hallucinations. Also created a LangGraph-based multi-agent academic paper search system integrating Tavily, arXiv, and Semantic Scholar with an orchestrator that routes tasks to specialized sub-agents.”

“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.”