Vetted MLflow Professionals

“AI/ML engineer with forensic analytics and healthcare claims experience (Optum), building production LLM/RAG systems to surface context-driven fraud patterns from unstructured claim notes and explain risk to investigators. Strong in large-scale retrieval performance tuning, legacy API integration with reliability patterns (SQS, circuit breakers), and MLOps orchestration on Airflow/Kubernetes with rigorous testing, monitoring, and stakeholder-friendly interpretability.”

“Built and deployed an LLM-powered financial/regulatory document analysis platform at State Street, combining fine-tuned transformer models with a RAG pipeline over internal knowledge bases. Owned the productionization stack (FastAPI, Docker, SageMaker, Terraform, CI/CD) plus monitoring for drift/latency/hallucinations, delivering ~40% faster analyst review and improved reliability through chunking/embeddings and grounding.”

“IBM engineer who built and deployed a production RAG-based LLM assistant using LangChain/FAISS with a fine-tuned LLaMA model, served via FastAPI microservices on Kubernetes, achieving 99%+ uptime. Demonstrates strong practical expertise in reducing hallucinations (semantic chunking + metadata-driven retrieval) and managing latency, plus mature MLOps practices (Airflow/dbt pipelines, MLflow tracking, monitoring, A/B and shadow deployments) and effective collaboration with non-technical stakeholders.”

“Built and deployed a production LLM-powered financial risk and compliance platform to reduce manual trade exception handling and speed up insights from regulatory documents. Implemented a LangChain multi-agent workflow with structured/unstructured data integration (Redshift + vector DB) and emphasized hallucination reduction for regulatory safety using Amazon Bedrock. Strong MLOps/orchestration background across Kubernetes, Airflow, Jenkins, and monitoring/testing with MLflow, Evidently AI, and PyTest.”

“At CVS Health, the candidate productionized a RAG-based LLM solution in a regulated healthcare setting, emphasizing reliable data pipelines, LoRA fine-tuning, monitoring, safety guardrails, and A/B testing. They have hands-on experience troubleshooting real-time RAG failures (e.g., chunking/embedding issues) and regularly lead developer-focused demos/workshops while translating technical architecture into business value for stakeholders.”

“Research Assistant at the University of Houston who built and live-deployed a production RAG system for 1000+ research documents, using hybrid retrieval (dense+BM25+RRF) with cross-encoder reranking and RAGAS-based evaluation; reported 66% MRR, 0.85+ faithfulness, and 68% lower LLM inference costs. Also built a deployed LangGraph multi-agent research system (Researcher/Critic/Writer) with tool integrations (Tavily, arXiv) and dual memory (ChromaDB + Neo4j), plus freelance automation work delivering a WhatsApp chatbot and n8n workflows for a wholesale clothing business.”

“Solutions Engineer specializing in taking LLM copilots from demo to production, with a strong emphasis on enterprise security (RBAC/OAuth), grounded RAG behavior (cite-or-refuse), and operational readiness (eval loops, logging, runbooks). Experienced in real-time diagnosis of agentic/LLM workflow failures and in partnering with Sales/CS to run integration-first POCs that clear security and reliability concerns and accelerate rollout.”

“Backend engineer who built and evolved a PHI-compliant RAG system (FastAPI + LangChain + embeddings/FAISS) for internal document search and summarization, delivering <400ms p95 latency at ~2,500 daily requests and measurable impact (30% faster investigations, +17% retrieval relevance). Demonstrates strong security and rollout discipline (RBAC/RLS/JWT, redaction/audits, shadow mode, dual writes, canaries) and a focus on reducing hallucination risk via grounded guardrails and confidence-based fallbacks.”

“Built and deployed a production LLM-powered RAG assistant for healthcare teams (care managers/support) to answer questions from clinical and policy documentation, emphasizing trustworthiness via improved retrieval, reranking, and strict grounding prompts to reduce hallucinations. Also has hands-on orchestration experience with Apache Airflow for end-to-end ETL/ML workflows and applies rigorous testing/metrics (hallucination rate, tool-call accuracy, latency, cost) to ensure reliable AI agent behavior.”

“ML/AI engineer with healthcare payer experience (Signal Healthcare, Cigna) who has shipped production fraud/claims prediction systems using Python/TensorFlow and exposed them via FastAPI/Flask microservices integrated with EHR and Salesforce. Emphasizes operational reliability and trust—Airflow-orchestrated pipelines with data quality gates plus SHAP-based interpretability, A/B testing, and drift/debug workflows—backed by reported outcomes of 22% lower false payouts and 17% higher model accuracy.”

“LLM/agentic systems engineer who built a production "Agentic AI Diagnostic Assistant" for network engineers, using a multi-agent Llama 2 + LangChain architecture with RAG over telemetry/incident data in DynamoDB and confidence-based deferrals to reduce hallucinations. Also has strong MLOps/orchestration experience (Airflow, EventBridge, Spark, Docker, SageMaker/ECS) at multi-terabyte/day scale and delivered multilingual NLP analytics (fine-tuned BERT/spaCy) for support operations through hands-on stakeholder workshops.”

“Built production LLM/RAG platforms for financial services to enable natural-language Q&A over large policy/compliance document sets stored in Snowflake and SharePoint. Strong in MLOps and orchestration (Airflow, ADF, Step Functions, MLflow) and in solving real production issues like stale embeddings and model performance, including an incremental Snowflake Streams sync that cut processing time from hours to minutes.”

“Built a production multi-agent LLM system at Live Nation on Databricks (LangGraph/LangChain) that let venue/event teams ask questions in Slack, auto-generated optimized route schedules, and produced inventory/stocking recommendations from historical SQL data and venue trends. Improved reliability by tightening prompts with strict JSON schemas, providing sample questions/SQL, and adding guardrails plus synthetic/edge-case testing, while iterating with event managers and senior VPs via prototypes and feedback loops.”

“Built a production internal LLM/RAG assistant at CVS Health to cut time spent searching long policy and clinical guideline PDFs, combining fine-tuned BERT/GPT models with FAISS retrieval and a FastAPI service on AWS. Demonstrates strong real-world reliability work (document cleanup, hallucination controls, monitoring/drift tracking with MLflow) and close collaboration with non-technical clinical operations teams via demos and feedback-driven iteration.”

“Built and deployed a production clinical claim validation RAG system at GE HealthCare that automated nurses’ patient-history/claims checks, cutting manual review time by ~65%. Designed the full stack (retrieval, embeddings, Pinecone, prompt/verification guardrails, FastAPI backend) with PHI-compliant anonymization via NER and orchestrated pipelines using Airflow, Azure ML Pipelines, and MLflow with drift monitoring.”

“GenAI/LLM engineer who recently built a production compliance assistant at State Farm for KYC/AML and regulatory teams, using AWS Bedrock + LangChain with Textract/Lambda pipelines to extract fields, tag risk, and summarize long documents. Implemented RAG, strict structured outputs, and human-in-the-loop guardrails, and reports automating ~80% of documentation work while reducing review time by ~40%.”

“Applied ML/embodied AI practitioner who built an on-device gesture-control system for smart-home lights using Raspberry Pi + camera, focusing on privacy-preserving real-time inference and hardware-constrained optimization (async pipeline + TF Lite INT8). Also made a high-impact architecture decision for an ML content evaluation/QA pipeline processing millions of annotated text samples weekly, reducing batch runtime from ~6 hours to ~40 minutes while lowering compute cost.”

“ML/AI engineer with defense and commercial analytics experience: deployed a real-time aerial object detection system at Dynetics (YOLOv5 + TorchServe in Docker on AWS EC2) with drift-triggered retraining and 99.5% uptime, tackling ambiguous targets and weather degradation. Previously at Fractal Analytics, built and explained a churn prediction model for marketing stakeholders using SHAP and delivered it via a Flask API into dashboards, driving a reported 22% attrition reduction.”

“ML/NLP practitioner focused on financial-services document intelligence and compliance workflows—built an end-to-end pipeline to classify documents and extract financial entities from loan applications, emails, and statements stored in S3/internal databases. Strong in entity resolution/record linkage and in productionizing pipelines with GitHub Actions CI/CD, testing, data validation, and Docker, plus semantic search using OpenAI embeddings and a vector database.”

“ML/NLP practitioner with banking experience (M&T Bank) who has built a GPT-4 RAG system using LangChain and Pinecone to connect unstructured customer data with internal knowledge bases, improving accuracy and reducing manual lookup time by 50%+. Strong in entity resolution and productionizing scalable Python data workflows, including major performance wins by migrating bottleneck joins from Pandas to Dask.”

“Full-stack engineer with healthcare and finance experience who has owned end-to-end production systems across Azure and AWS. Built a real-time clinical dashboard at Centene (React + FastAPI + Azure Event Hubs) that cut data latency from ~12 minutes to under 1 minute and was associated with a 30% reduction in intervention delays. Also delivered MVPs in high-ambiguity environments at Accenture during monolith-to-microservices migration, improving uptime and maintainability with measurable results.”

“AI/LLM engineer who has shipped production RAG systems (including a 250K-document compliance knowledge tool on AWS) and focuses on reliability via citations, guardrails, and rigorous evaluation (Ragas/Opik/DeepEval). Also built a LangGraph-orchestrated webcrawler agent that cut research paper extraction from hours to minutes, and collaborated with clinical teams to deliver patient volume forecasting with an optimization layer for staffing.”