Vetted Hugging Face Professionals

“Built and shipped a production RAG-based enterprise knowledge assistant to replace slow/inaccurate search across millions of documents, using LangChain orchestration with GPT-4/LLaMA and vector databases. Strong focus on production constraints—latency, hallucination control, and cost—using hybrid retrieval, guardrails, LLM-as-judge validation, and model routing, and has experience translating non-technical stakeholder pain points into measurable outcomes.”

“AI/LLM engineer who has shipped 10+ production applications, including InvestIQ on GCP—a production-grade RAG due-diligence engine that ethically scrapes web/PDF sources, builds a ChromaDB knowledge base, and delivers analyst-style dashboards plus a citation-backed chat copilot. Deep focus on reliability (evidence-only answers, hard citations, refusal gating), retrieval tuning, and orchestration (Airflow/Cloud Composer), plus multi-agent systems (CrewAI with 7 specialized finance agents).”

“BNY Mellon engineer who has built and operated production AI systems end-to-end: a LangChain/Pinecone RAG platform scaled via FastAPI + Kubernetes to 1000 RPM with 99.9% uptime, supported by monitoring and data-drift detection. Also deep in data/infra orchestration (Airflow, Dagster, Terraform on AWS/EMR/EC2), processing 500GB+ daily and delivering measurable reliability and performance gains, plus strong compliance-facing model explainability using SHAP and Tableau.”

“LLM/agentic workflow engineer with healthcare domain experience who built a HIPAA-compliant multi-agent RAG system for clinical review automation at UnitedHealth Group, achieving 92% precision and cutting latency 40% through async orchestration and Redis semantic caching. Also has strong data engineering orchestration background (Airflow on AWS EMR with Great Expectations) and a proven clinician-in-the-loop feedback process that improved model faithfulness by 18%.”

“Built and led deployment of an autonomous, self-correcting multi-agent knowledge retrieval and validation system at HCA Healthcare to reduce heavy manual research/validation in clinical/compliance documentation. Deeply focused on production reliability and cost—used LangGraph StateGraph orchestration plus ONNX/CUDA/quantization to cut GPU costs by 25%, and partnered with the Compliance VP using real-time contradiction-rate dashboards to hit a 40% automation goal without compromising compliance.”

“Built and deployed production LLM assistants for internal Q&A and customer-feedback summarization, emphasizing reliability (RAG, prompt tuning, validation/whitelisting) and privacy safeguards. Improved adoption by adding explainable outputs and a user feedback mechanism, and has hands-on orchestration experience with Aflow and Azure Logic Apps.”

“Backend engineer who significantly evolved an internal analytics/reporting platform (Python API + Postgres) powering self-service dashboards for product/business teams, focusing on reliability under heavy concurrent load and fast query performance. Demonstrates strong production engineering practices across API design (FastAPI), observability, incremental rollouts with feature flags, and data security using JWT/RBAC plus Postgres row-level security.”

“Healthcare-focused LLM engineer who deployed a production triage and clinical knowledge retrieval assistant using RAG and LangGraph-orchestrated multi-agent workflows. Emphasizes clinical safety and compliance with robust hallucination controls, HIPAA/PHI protections (tokenization, encryption, audit logging, zero-retention), and human-in-the-loop escalation; reports a 75% latency reduction in a healthcare agent system.”

“AI/LLM engineer who built a production intelligent support system using RAG over a vectorized documentation library, addressing real-world issues like lost-in-the-middle context failures and doc freshness via automated GitHub-driven re-embedding pipelines. Emphasizes rigorous agent evaluation (component/E2E/ops) and prefers lightweight, decoupled workflow automation using message brokers (Redis/RabbitMQ) over heavyweight orchestration frameworks.”

“Has production deployment experience delivering computer-vision systems on AWS (Docker + S3) including a GDPR-focused face/license-plate obfuscation pipeline and a semantic-segmentation project aimed at reducing annotation time. Worked closely with DevOps and frontend teams and partnered with CEO/CMO to present an AI-driven annotation workflow to non-technical VC stakeholders.”

“Research-focused AI/ML candidate who built an fMRI-based classifier to predict schizophrenia treatment effectiveness under small-dataset constraints. Demonstrated pragmatic model selection by moving from a complex GNN to graph-summary feature engineering with logistic regression, significantly improving accuracy and AUC; primarily works in Google Colab with script-based workflows.”

“Machine Learning Intern at Docsumo who delivered a customer-facing fraud-detection solution end-to-end: rebuilt the pipeline, deployed a Random Forest model, and shipped a Python/Flask microservice on AWS SageMaker. Drove measurable production impact (precision +30%, processing time cut in half, manual review -60%, customer satisfaction +15%) and demonstrated strong customer integration and live-incident response skills.”

“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.”

“Backend engineer who built a Python/Flask system for high-volume healthcare claims processing, using PostgreSQL as the source of truth and RabbitMQ workers for scalable async processing. Experienced in SQLAlchemy/Postgres performance tuning, multi-tenant data isolation (including Postgres RLS), and integrating/versioning ML model services (scikit-learn/PyTorch/Hugging Face) with controlled rollouts. Drove measurable performance gains by batching background jobs and adding Redis caching (40% less workload; response times cut from ~10s to 2–3s).”

“Built a production multimodal LLM-based vendor risk assessment platform that ingests SOC reports and other documents, uses a strict RAG pipeline with grounded evidence (page/paragraph citations), and dramatically reduces analyst review time. Experienced with LangGraph/LangChain/AutoGen for stateful, fault-tolerant agent workflows, and emphasizes reliability (schema validation, guardrails) plus low-latency delivery (~1–2s) through hybrid retrieval, reranking, caching, and model tiering.”

“Full-stack engineer at an early-stage startup building an agentic AI application for enterprise systems, combining customer-facing Next.js/React UI work (30% faster load times) with backend/workflow orchestration using FastAPI + n8n, Redis, and RabbitMQ. Previously at Deloitte USI, built BDD Selenium/Java automation and managed 200+ defects end-to-end using JIRA/JAMA to support on-time production releases.”

“Blue Prism RPA developer in a small FinTech-aligned team who owned ~20 production bots and drove both delivery and reliability. Built a shared VDI/locking design that cut infrastructure cost ~20–30% and routinely handled ServiceNow-driven production incidents end-to-end, including hotfixes and longer-term SDLC fixes. Also acted as a player-coach, training junior hires and maintaining high bot success rates (up to 99% within SLA).”

“Backend engineer who optimized an AI-driven portfolio analytics/insights platform at Fidelity, addressing latency and traffic growth by moving services toward microservices, improving service communication, and tuning API/DB performance. Experienced scaling Python/FastAPI services with Docker + Kubernetes autoscaling, and strengthening security/privacy for sensitive client portfolio data used in LLM-based reporting.”

“Built and deployed AcademiQ Ai, a production LLM-based teaching assistant using GPT/BERT with RAG (LangChain + Pinecone) to handle large student notes and generate adaptive explanations/quizzes. Demonstrated measurable retrieval-quality gains (18% precision improvement, 22% less irrelevant context) by tuning similarity thresholds and chunking based on user satisfaction signals. Also orchestrated terabyte-scale, real-time demand forecasting pipelines using Airflow and Kubeflow on GCP with strong monitoring, shadow deployment, and feedback-loop practices.”

“Full-stack engineer with financial services experience (Lincoln Financial) who owned a customer-facing financial portal end-to-end using TypeScript/React and Node/Express. Has hands-on microservices and RabbitMQ event-driven workflows, addressing scale issues like retries/duplicates with idempotency and traceable logging, and built an internal real-time ops/support dashboard to improve monitoring and incident response.”

“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 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 a production "appeals co-pilot" for a healthcare claims appeals team, combining an XGBoost/logistic ranking model with a Python/LangChain RAG stack (FAISS + Mistral 7B) to surface high-probability appeal wins and speed policy-grounded drafting. Emphasizes reliability and trust: hybrid retrieval with metadata routing, citation/eval scripts, guardrails, and an explainability layer that non-technical stakeholders could understand and override.”