Vetted FAISS Professionals

“Built and deployed a production LLM-powered multi-agent compliance copilot (life sciences/finance) using LangChain/LangGraph + RAG over vector databases, delivered via async FastAPI on Kubernetes. Emphasizes audit-ready, deterministic outputs with schema constraints and citations, plus rigorous evaluation/monitoring; reports 60%+ reduction in manual research time and successful production adoption.”

“LLM/agentic-systems engineer with PayPal experience hardening an LLM-powered fraud support assistant from prototype to production, focusing on low-latency distributed architecture, rigorous evaluation/testing, and security/compliance. Comfortable in customer-facing and GTM contexts—runs technical demos/workshops, builds tailored pilots, and aligns sales/CS with engineering to close deals and drive adoption.”

“Built and productionized a telecom-focused RAG assistant by LoRA fine-tuning LLaMA-2 and integrating LangChain+FAISS behind a FastAPI service, with dashboards and a human feedback UI for engineers. Demonstrated measurable impact (≈40% faster document lookup, +8–10% retrieval precision) and strong MLOps rigor via Airflow orchestration, CI/CD, and monitoring for drift and failures.”

“Built and deployed a production Retrieval-Augmented Generation (RAG) platform in a healthcare setting to automate clinical documentation review and summarization, targeting near-real-time, explainable outputs. Emphasizes grounded generation to reduce hallucinations, latency optimizations (chunking/embedding reuse), and PHI-safe workflows with access controls, plus strong orchestration experience using Apache Airflow.”

“Built an LLM-powered learning assistant (EduQuizPro/EduCrest Pro) that uses RAG over URLs and PDFs to generate quizzes, notes, and explanations for students/professors. Emphasizes production robustness—implemented dependency fallbacks (FAISS/Sentence Transformers/Gradio), CLI-safe mode, and NumPy-based indexing—along with a custom orchestration layer to keep multi-step AI workflows reliable.”

“Built a production GenAI-powered analytics assistant to reduce reliance on data analysts by enabling natural-language Q&A over Databricks/Power BI dashboards, backed by vector search (Pinecone/Milvus) and a Neo4j knowledge graph, including multimodal support via OpenAI Vision. Demonstrates strong real-world LLM reliability engineering with strict RAG, LangGraph multi-step verification, and Guardrails/custom validators, plus broad orchestration and production monitoring experience (Airflow, ADF, Step Functions, Kubernetes, Prometheus/CloudWatch).”

“ML/NLP engineer currently working in NYC on a system that connects complex unstructured data sources to deliver personalized insights, using embeddings + vector DB retrieval and a RAG architecture (LangChain, Pinecone/OpenSearch). Strong focus on production constraints—especially low-latency retrieval—using FAISS/ANN, PCA, index partitioning, and Redis caching, plus PEFT fine-tuning (LoRA/QLoRA) and KPI/SLA-driven promotion to production.”

“Built a production RAG-based GenAI copilot backend at Aetna using Python/FastAPI, GPT-4, LangChain, and Azure AI Search, deployed on AKS with Prometheus/Grafana observability. Owned the system end-to-end (ingestion through deployment) and improved peak-time reliability by addressing vector search and embedding bottlenecks with Redis caching, index optimization, and async processing, plus added anti-hallucination guardrails via retrieval confidence thresholds.”

“Built and productionized an AI-native, agentic appeals decisioning system for health insurance operations, automating 500k+ scanned appeals/year. Delivered measurable impact by cutting review time from 12–15 minutes to ~3 minutes and auto-resolving ~85% of cases with strong auditability, evaluations, and human-in-the-loop guardrails, deployed as containerized microservices on Azure AKS.”

“LLM engineer who built a production seller-support RAG system at eBay using hybrid retrieval (BM25 + Pinecone vectors) with Cohere reranking, LangGraph orchestration, and citation-grounded answers. Strong focus on reliability: semantic/structure-aware chunking, automated Ragas-based evaluation with nightly regressions, and production observability (LangSmith) plus drift monitoring (Arize). Also implemented a multi-agent fraud pipeline with AutoGen using JSON-schema contracts and explicit termination conditions.”

“Backend/AI workflow engineer who built production-grade orchestration systems for hardware security verification at Silicon Assurance (Nextflow/Python/Postgres) and a multi-agent LLM-driven regulatory code checking system at the University of Florida. Emphasizes reliability: strict plan/execute/verify boundaries, queue-based isolation, and strong observability/auditability with Prometheus/Grafana and persisted prompts/tool calls.”

“LLM engineer who has deployed production RAG systems for regulated document QA (PDFs/knowledge bases), emphasizing grounded answers with citations, RBAC, monitoring, and continuous feedback. Demonstrates deep practical expertise in retrieval quality (semantic chunking, hybrid BM25+embeddings, re-ranking), reliability (guardrails, deterministic workflows), and measurable evaluation (golden sets, log replay, A/B tests) while partnering closely with compliance/operations stakeholders.”

“Backend/ML engineer who built production LLM-enabled systems at PRGX, including an interpretable contract opportunity scoring engine (Bradley-Terry pairwise ranking) that reached 0.82 weighted Spearman agreement with SME auditors and was integrated into workflow. Also built a Duke student advisor chatbot and hardened it for real-world reliability/security with schema-driven tool calling, normalization, and off-domain defenses; led staged production rollouts with shadow testing and achieved 0.90 F1 on a new extraction field before shipping.”

“At JP Morgan Chase, built and deployed a production LLM-powered RAG knowledge assistant to help fraud investigators and risk analysts quickly navigate regulatory updates and internal policies, reducing investigation delays and compliance risk. Strong focus on secure retrieval (RBAC filtering), reliability (layered testing + observability), and production constraints (latency/SLOs), with Airflow-orchestrated, auditable ML pipelines.”

“Built and deployed a production GenAI internal support agent at Bank of America (“Ask GPS/AskGPT”) using RAG on Azure, focused on reducing escalations and improving response quality for repetitive knowledge-based queries. Demonstrates strong production LLM engineering: custom LangChain orchestration, retrieval tuning to reduce hallucinations, rigorous offline/online evaluation, and model benchmarking with dynamic routing (e.g., GPT-4 vs Claude).”

“LLM/RAG engineer who has built and deployed corporate-scale systems at Novartis and Johnson & Johnson, including a healthcare AI agent that generates day-to-day treatment schedules. Recently handled a high-stakes safety incident (LLM suggesting overdose) by tightening model instructions and validating with ~200 test prompts, and has strong end-to-end data/embedding/vector DB pipeline experience (PySpark, FAISS, Pinecone) plus SME-in-the-loop evaluation (RLHF).”

“Built and shipped a production LLM-powered personalized client engagement assistant in the financial domain, balancing real-time recommendations with strict privacy/compliance requirements. Demonstrates strong MLOps/LLMOps depth (Airflow + MLflow, containerized microservices, drift monitoring) and a privacy-by-design approach validated in collaboration with risk and compliance teams.”

“At Fileread, the candidate built and deployed an LLM-powered legal document classification and retrieval layer for an agentic extraction system that turns unstructured legal PDFs into structured tables with line-level citations. They productionized a RAG-style pipeline (ingestion, embeddings, retrieval, reranking, generation) and report 95%+ F1 across 70+ legal categories, emphasizing rigorous evaluation and close collaboration with legal domain experts for high-stakes precision.”

“Built and productionized an autonomous research agent (AutoGPT) in a Docker/Kubernetes environment with Pinecone-based long-term memory and custom Python tools for analysis, visualization, and report drafting. Implemented layered guardrails (prompt templates, automated validation, self-critique loops, and monitoring) and achieved ~25% reduction in manual report generation time while scaling the workflow to support multiple concurrent users.”

“Built and deployed a production LLM + vector search clinical decision support system at UnitedHealth Group, retrieving medical evidence and patient context in real time for prior authorization and risk scoring. Strong in end-to-end RAG architecture (Hugging Face embeddings, Pinecone/FAISS, SageMaker, Redis) plus orchestration (Airflow/Kubeflow) and rigorous evaluation/monitoring, with demonstrated ability to align solutions with clinical operations stakeholders.”

“AI/ML engineer with HP experience building and productionizing an LLM-powered document intelligence platform (LangChain + Pinecone) to deliver semantic search and contextual Q&A across millions of enterprise support documents. Demonstrates strong MLOps and scaling expertise (Airflow, Kubernetes autoscaling, Triton GPU inference, monitoring with Prometheus/W&B) plus a structured approach to evaluation (A/B tests, shadow deployments, failover) and effective collaboration with non-technical stakeholders.”

“GenAI/data engineering practitioner with production experience across Equinix, Optum, and Citibank—built an Azure OpenAI (GPT-4) + LangChain document intelligence platform processing 1.5M+ docs/month and a HIPAA-compliant Airflow healthcare pipeline handling 5M+ claims/day. Also delivered a real-time fraud detection + explainability system using LightGBM and a fine-tuned T5 NLG component, improving fraud accuracy by 15%+ while partnering closely with compliance stakeholders.”

“Internship experience building a production RAG+LLM pipeline to map messy card transaction descriptions to merchant brands, including a custom modified-ROUGE evaluation approach for weak/variant ground truth. Improved scalability and cost by moving from a managed LLM endpoint (e.g., Bedrock) to self-hosted vLLM, and orchestrated massive embedding backfills (5,000+ files, 10B+ rows) using an Airflow-triggered SQS + ECS worker architecture with robust retry/DLQ handling.”

“Built and deployed a secure, production LLM-based document summarization and risk-highlighting tool for financial auditors, running inside a private Azure environment to protect confidential data. Focused on reliability (hallucination mitigation via retrieval-based prompts and source citations) and validated performance through comparisons to auditor summaries plus a user pilot, cutting review time by about half.”