Vetted LangGraph Professionals

“Asset Management Risk professional at Fidelity Investments who built and productionized an agentic RAG platform enabling compliance and analysts to query 10,000+ fund documents with cited answers in seconds. Implemented structure-aware semantic chunking (AWS Textract), hierarchical retrieval, and hybrid search to raise accuracy from 68% to 94%, and built an evaluation framework tracking accuracy/latency/cost/hallucinations—delivering 40+ hours/month saved and zero critical production failures.”

“Backend engineer with experience in both regulated healthcare and finance: built a multi-agent RAG system to generate FDA regulatory approval documents for biomedical devices, improving retrieval accuracy via hybrid search (semantic + BM25) and hierarchical chunking. Previously at JPMorgan Chase, led a Java microservice refactor and AWS migration using Elasticsearch-first patterns, caching, and safe rollout strategies (parallel runs, canary, blue-green) in asset/wealth management.”

“ML/GenAI practitioner with healthcare domain depth who built and deployed a production cervical-cancer EMR classification system using a hybrid rules + medical BERT approach, optimized for high recall under severe class imbalance and PHI constraints. Experienced running end-to-end production ML/LLM pipelines with Apache Airflow (validation, promotion/rollback, monitoring, retraining) and partnering closely with clinicians to calibrate thresholds and implement human-in-the-loop review.”

“LLM/agent engineer who has shipped production RAG chatbots in sustainability-focused domains, including a packaging recommendation assistant that standardized messy user inputs and used Pinecone-backed retrieval over product/regulatory data. Experienced orchestrating end-to-end ML workflows with Airflow and AWS Step Functions/Lambda, emphasizing reliability (property-based testing, circuit breakers, OpenTelemetry) and measurable performance (latency/cost). Partnered closely with non-technical leadership to ship 3 weeks early, driving adoption by 150+ businesses and ~20% reported waste reduction.”

“Co-founder of an HR tech startup who took an LLM-centered skill intelligence engine from prototype to production to deliver explainable, skill-based resume insights as an alternative to black-box ATS screening. Previously worked in consulting (Deloitte, Stand Up, Brilio), with experience in technical demos/workshops, pre-sales scoping, and supporting large deal cycles (including a ~$1M UK automotive client).”

“Built and shipped a production-grade GenAI Fraud & Compliance Investigation Copilot for a large US bank, integrating OCR docs, structured data, and prior case history to generate grounded, regulator-friendly summaries and red-flag highlights. Demonstrates strong end-to-end LLM systems engineering (LangGraph/LangChain, hybrid retrieval with FAISS+BM25, guardrails/citations, streaming/latency optimization) plus rigorous evaluation and close partnership with compliance stakeholders.”

“Backend engineer who built a Python-based data profiling/statistics platform processing up to 50M rows and ~300 metrics, using a DAG execution model, multithreading, and smart caching to cut processing time by up to 70%. Also improved PostgreSQL query performance from 12s to 2s via indexing/query rewrites, integrated an LLM (LangChain + OpenAI) for explainable “chat with the pipeline” functionality, and designed an AWS EC2+SQS architecture for scalable, isolated per-user processing.”

“Software engineer with experience at Google and the City and County of San Francisco building production AI systems, including a RAG-based internal support chatbot and ML-driven ticket priority tagging. Has scaled data/ML platforms with Airflow on GCP (1M+ records/day, 99.9% SLA) and deployed multi-component systems with Docker and Kubernetes (GKE), using modern LLM tooling (LangChain/CrewAI, Claude/OpenAI, Pinecone/ChromaDB, Bedrock/Ollama).”

“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).”