Vetted FAISS Professionals

“ML/NLP practitioner who built a retrieval-augmented generation (RAG) system for large financial and operational document sets using Sentence-Transformers (all-mpnet-base-v2) and a vector DB (e.g., Pinecone), with a strong focus on retrieval evaluation and chunking strategy optimization. Experienced in entity resolution (rules + embedding similarity with type-specific thresholds) and in productionizing scalable Python data workflows using Airflow/Dagster and Spark.”

“Built an AI lending assistant (RAG + DeBERTa) used by credit analysts to retrieve policies and past loan decisions, tackling real production issues like hallucinations, document quality, and sub-second latency. Deployed a modular, Dockerized AWS architecture (ECS/EMR + load balancer) with load testing, caching/precomputed embeddings, and CloudWatch monitoring, and used Airflow to automate scheduled data/embedding/vector DB refresh pipelines with retries and alerts.”

“AI/ML Engineer who built a production RAG-based LLM system for insurance policy documents, turning thousands of messy PDFs into a searchable index using LangChain, Azure AI Search vectors, hybrid retrieval, and FastAPI. Strong focus on evaluation (MRR/precision@k/recall@k, REGAS) and performance optimization (vLLM), with prior clinical NLP experience using BERT-based NER validated on ground-truth datasets.”

“Built a secure, on-prem/private GPT assistant to replace manual SharePoint-style search across thousands of policies/SOPs/engineering docs, using a production RAG stack (LangChain/LangGraph, FAISS/Chroma, PyMuPDF+OCR, vLLM). Implemented layout-aware ingestion (including table-to-JSON) and a multi-agent retrieval/generation/verification workflow with strong observability and compliance guardrails, delivering ~70% reduction in search time.”

“Recent J&J intern who built a conversational RAG agent and led a shift from a monolithic model to a modular RAG workflow, cutting response time from several days to under a second by tackling data fragmentation, context retention, and embedding/latency optimization. Also worked on a large (7B-parameter) multimodal VQA pipeline for healthcare research and stays current via NeurIPS/ICLR and open-source contributions.”

“ML/AI practitioner with hands-on experience deploying models to production and optimizing for low-latency inference using pruning/quantization, with deployments on AWS SageMaker and Azure ML. Has orchestrated end-to-end ML pipelines with Airflow and Kubeflow (ingestion through evaluation) and emphasizes reproducibility via containerization and version-controlled artifacts, while effectively partnering with non-technical stakeholders using dashboards and business-aligned metrics.”

“Data/ML practitioner with experience at Airtel and Lincoln Financial delivering measurable business outcomes: improved retention 15% via NLP sentiment analysis and cut response time ~25% using sentence-BERT + FAISS semantic linking. Strong in data quality/identity resolution (SQL + fuzzy matching) and in building production-grade Python workflows orchestrated with Airflow/AWS Glue, including validation and dashboard integration in Power BI.”

“Built and shipped a production LLM-powered RAG system at Upstart enabling natural-language search across 50k+ scattered internal technical docs. Delivered sub-300ms p95 latency for ~50 active users with strong hallucination safeguards (retrieval-first, thresholds, citations) plus robust testing/monitoring and cost controls (prompt caching cutting API spend ~20%).”

“GenAI engineer who has deployed production LLM/RAG chatbots for internal document search, focusing on reliability (hallucination reduction via prompt guardrails + retrieval filtering) and performance (latency improvements via caching). Experienced with LangChain/LangGraph orchestration for multi-step agent workflows and iterates using monitoring/logs and benchmark-driven evaluation while partnering closely with product and business teams.”

“Backend engineer focused on AI-enabled systems, having built a production-style RAG pipeline (vector search + LLM) exposed via Python/Flask endpoints with strong observability and hallucination-reduction techniques. Demonstrates deep performance work in PostgreSQL/SQLAlchemy (5x faster analytics queries) and high-throughput optimization using Celery + Redis (800ms to 120ms latency, 3x throughput), plus schema-per-tenant multi-tenancy with tenant-aware middleware and logging.”

“Robotics software engineer who built the software layer for an autonomous warehouse sorting system, spanning navigation/path planning, task scheduling, and backend services. Deep hands-on ROS 2 Foxy experience (Nav2/costmaps) and real-time multi-robot debugging, using simulation-driven analysis plus incremental/partial re-planning to handle dynamic obstacles in production-like warehouse environments.”

“Built and deployed a production real-time voice AI support agent that answers inbound calls, identifies callers, troubleshoots via a knowledge base, and automatically creates/updates tickets with escalation to humans when needed. Demonstrates strong reliability/latency engineering (streaming, schema validation, idempotency, DB constraints) and uses LangGraph state machines plus OpenAI Agents SDK for multi-agent routing, with KPI-driven testing and monitoring.”

“JavaScript/React performance-focused engineer who contributed upstream to an open-source virtualization/pagination library, fixing overlapping-fetch race conditions and introducing prefetch/deduping patterns that cut load times from ~3s to <900ms and reduced render thrash ~35%. Also built healthcare automation systems (clinical summary and claims triage), including a FastAPI + RAG pipeline that retrieved CPT/ICD evidence, improving decision accuracy from 67% to 86% and reducing turnaround time by 40%.”

“Built production LLM + hybrid RAG and multi-agent orchestration systems at Wells Fargo to automate complaint document/audio transcript understanding and categorization, addressing vocabulary drift via embedding + vector index updates instead of frequent retraining. Strong in LLM workflow reliability (testing/benchmarks/observability) and stakeholder-facing delivery with explainability (citations/SHAP-style justifications) and Tableau dashboards.”

“ML/NLP engineer with experience at Charles Schwab building an NLP + graph (Neo4j) entity-resolution system to unify fragmented user/device/transaction data and improve downstream model quality and analyst querying. Has applied embeddings (SentenceTransformers + FAISS) with domain fine-tuning to boost hard-case matching recall by ~12% while maintaining precision, and has a track record of hardening scalable Python/Spark pipelines and productionizing fraud models via A/B tests and shadow-mode monitoring.”

“Built and shipped a production RAG-based assistant that lets parents ask natural-language questions about their child’s learning progress, using pgvector retrieval (child-id filtered) and Redis caching to hit ~180ms latency. Implemented real-world guardrails and compliance (Llama Guard, COPPA, retrieval thresholds, fallbacks) with 99.5% uptime, and ran human-in-the-loop eval loops that improved satisfaction from 3.8 to 4.2 while serving 60k+ monthly users and reducing costs significantly.”

“Built and scaled an AI-powered voice/chat patient engagement platform at Penn Medicine from early prototype into production clinical workflows, focusing on latency, edge cases, and user trust. Strong in LLM reliability engineering (structured prompts, validation/fallbacks), real-time troubleshooting with observability, and cross-functional enablement through pilots, demos, and sales/customer partnership.”

“Founding member of Tausight, building AI systems to detect and protect PHI for healthcare organizations; helped take the company through post–Series A funding and exited after ~6 years. Drove a strategic collaboration with Intel’s OpenVINO team—becoming the first to deploy it in a real production system and improving model performance by ~30% on customer Intel-CPU machines.”

“AI/LLM engineer with published work who built FinVet, a production financial misinformation detection system using multi-pipeline RAG, confidence-based voting, and evidence-backed outputs (F1 0.85, +37% vs baseline). Also built NexusForest-MCP, a Dockerized Model Context Protocol server exposing structured global deforestation/carbon data via SQL tools for reliable LLM tool use. Previously delivered borrower risk-rating (PD) models at BMO Financial Group that were validated and integrated into an enterprise credit system through close collaboration with credit officers and portfolio managers.”

“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.”

“Built and productionized an enterprise retrieval-augmented generation platform for internal knowledge over large unstructured corpora, emphasizing trust via strict citation/grounding and hybrid retrieval (BM25 + FAISS + cross-encoder re-ranking). Demonstrates strong scaling and cost/latency optimization through incremental indexing/embedding and index partitioning, plus disciplined evaluation/observability practices. Has experience operationalizing pipelines with Airflow/Databricks/GitHub Actions and partnering closely with risk & compliance stakeholders on auditability requirements.”

“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 shipped production generative AI/RAG assistants in regulated financial contexts (S&P Global), automating compliance-oriented Q&A over earnings reports/filings with grounded answers and citations. Experienced across the full stack—AWS-based ingestion (PySpark/Glue), vector retrieval + LangChain agents, GPT-4/Claude model selection, and production reliability (monitoring, caching, retries) plus rigorous evaluation and regression testing.”

“AI/LLM engineer with production experience in legal tech: built a GPT-4 + LangChain RAG summarization system at Govpanel that reduced legal case-file review time by 50%+. Previously at LexisNexis, orchestrated end-to-end Airflow data/AI pipelines processing 5M+ legal documents daily, improving ETL runtime by 35% with robust validation, monitoring, and SLAs.”