Vetted FAISS Professionals

“Built and deployed LLM-powered features for a startup organizational management application, focusing on real-world deployment constraints like latency and cost. Implemented RAG with FAISS and improved retrieval quality by switching embedding models (OpenAI/Hugging Face) and fine-tuning embeddings on medical corpora for a medical-report UI feature. Uses LangChain and LangGraph to orchestrate multi-node LLM API workflows and evaluates systems with metrics like latency, cost per request, and error taxonomy.”

“Built a LangGraph-based, tool-routing LLM chatbot to deliver fast, trustworthy investment-stock insights (including tariff impact) and deployed it to production on Snowflake after initially developing in Azure with AI Search and the Microsoft Agent Framework. Improved routing robustness by moving from LLM-based decisions to a deterministic router backed by schema-relationship graphs and YAML metadata, and ran the project iteratively with non-technical stakeholders over an 8-month engagement.”

“Built and deployed a production LLM-powered text-to-SQL/document intelligence chatbot on AWS that lets non-technical business users query complex enterprise databases in plain English. Demonstrates deep practical expertise in schema-aware prompting, embeddings-based schema retrieval, SQL safety/validation guardrails, and rigorous offline/online evaluation with human-in-the-loop approvals for risky queries.”

“Built a production-grade LLM evaluation and regression system that stress-tests models across hundreds of iterations, combining LLM-as-judge, semantic similarity, statistical metrics, and rule-based checks, with results delivered via stakeholder-friendly HTML reports and dashboards. Experienced orchestrating multi-agent RAG workflows using LangChain/LangGraph and event-driven GenAI pipelines in n8n integrating OCR, speech-to-text, and external APIs, with strong emphasis on reliability, observability, and explainable failures.”

“Applied LLMs to classify long nonprofit mission statements into 8 segments without labeled data, using an ensemble of clustering/embedding methods plus zero-shot RoBERTa/BART and a Tree-of-Thought prompting pipeline with LLM-as-judge evaluation (Gemma). Also built LangChain/LlamaIndex agentic RAG workflows including a text-to-SQL data analysis assistant grounded on DB schema with retries and performance optimizations on an HPC cluster.”

“Built a production-grade, semi-automated document recognition and classification system for large volumes of scanned PDFs, starting from little/no labeled data and handling highly variable scan quality. Deployed on AWS using SageMaker + Docker and orchestrated on EKS with a microservices design that scales CPU-heavy OCR separately from GPU inference, with strong reliability controls (validation, fallbacks, retries, readiness probes).”

“Built and deployed an LLM product called "Content Craft" combining BART-based summarization with a RAG Q&A chatbot using LangChain, embeddings, and a vector database. Has hands-on MLOps experience containerizing and serving models with FastAPI and running them on Kubernetes with monitoring, self-healing, and autoscaling, and has practical experience reducing hallucinations through structured prompting.”

“LLM/agentic AI builder who deployed a production ITSM automation agent on Google ADK integrating ServiceNow and FreshService, with strong safety guardrails (human-approval gating and runbook-only command execution) and rigorous evaluation (500 synthetic tickets; 80%+ false-positive reduction). Also partnered with finance to deliver an AI agent that automated invoice/SOW retrieval and monthly reporting to account managers, reducing manual back-and-forth.”

“Built and deployed a production-grade, multi-agent Text-to-SQL assistant that lets non-technical stakeholders query large enterprise databases in natural language. Uses Pinecone-based schema retrieval + LLM reasoning (Gemini/Claude/GPT) with a dedicated validation agent (schema/syntax checks and safe dry runs) to reduce hallucinations and improve reliability, while optimizing latency and cost via async execution and embedding caching.”

“Backend/applied AI engineer from Cloud Rack Systems who built production GenAI/RAG and data platforms on Azure/Databricks at enterprise scale (2.5M records/day). Known for making LLM systems behave like deterministic services via strict retrieval contracts, citation-based validation, and strong observability—shipping a knowledge assistant used daily by 50+ users while driving hallucinations near zero and materially improving latency and cost.”

“Built and deployed a production RAG-based clinical decision support assistant at MedLib, focused on fast, trustworthy answers from large medical documents. Demonstrates deep practical experience improving retrieval accuracy (semantic chunking + metadata-aware search), controlling hallucinations with grounded generation and thresholds, and adding clinician-requested citations using chunk metadata, with evaluation driven by healthcare professional review.”

“Backend engineer specializing in event-driven/serverless systems and Python/FastAPI APIs. Built a scalable PDF-to-structured-data pipeline on AWS (S3, Lambda, Step Functions, Textract, DynamoDB, SNS) with strong observability (p50/p90/p99) and reliability patterns (idempotency, retries/DLQs), and has led zero-downtime migrations using feature flags, dual writes, and incremental rollouts.”

“Built a real-time AI meeting assistant using a Chrome extension that streams audio to a backend LLM workflow with transcription and RAG, then hardened it for production with queue-based streaming, async pipelines, security controls, and full observability. Also has hands-on startup sales experience, partnering with customers to define measurable technical win conditions (latency/accuracy) to close deals and drive adoption.”

“Customer-facing software engineer who builds and deploys practical AI/RAG solutions (e.g., an AI assistant for searching billing PDFs) by deeply understanding support workflows and iterating with users. Demonstrates strong production instincts—quickly stabilizing peak-traffic API timeouts with caching/background jobs, then implementing durable fixes with proper monitoring and maintainable code practices.”

“LLM engineer/data analyst who built a production RAG QA assistant over the Jurafsky & Martin NLP textbook to reduce hallucinations and provide explainable, source-grounded answers. Experienced with LangChain/LangGraph orchestration, retrieval optimization (embeddings, vector DBs, caching), and rigorous evaluation/monitoring (Retrieval@K, A/B tests, telemetry/drift). Previously communicated analytics insights to non-technical stakeholders at GS Analytics using Power BI and simplified reporting.”

“Forward Deployed Engineer at EasyBee AI who productionized a self-storage customer’s multi-agent LLM system end-to-end—rebuilding it with LangGraph/CrewAI, integrating with real property management + CRM systems via an MCP server, and adding observability/guardrails for reliable daily use. Experienced in live troubleshooting of agentic workflows, developer demos/workshops (including an open-source project, MerryQuery), and partnering with sales to close deals through customer-specific technical demos and fast integration feedback loops.”

“Internship at Discovery Education building a production LLM/RAG chatbot that let marketing and sales teams query and interpret Looker/BI dashboards in natural language, with responses grounded in compliance and state education standards. Emphasizes rigorous evaluation (faithfulness/precision/recall/latency) plus user-feedback analytics, and used LangChain for orchestration, chunking/context-window control, and integration with enterprise sources like SharePoint.”

“Full-stack engineer operating in early-stage, high-velocity environments (OpGov.AI/UST Calibrate) who ships production Next.js App Router features end-to-end (RSC, Server Actions, SEO, RBAC, caching) and owns performance post-launch. Demonstrates strong data/infra depth—designed Postgres JSONB-based event models for DevOps/DORA analytics and tuned queries from ~2s to <50ms, plus built durable ingestion workflows with retries and idempotency on Azure.”

“Full-stack engineer who has shipped and operated generative-AI chat/QA features end-to-end, including a RAG-based pipeline with guardrails and cost/latency monitoring in production. Experienced with React/TypeScript + Node/Postgres architectures, Dockerized deployments to AWS (EC2) via GitHub Actions CI/CD, and building reliable ingestion/ETL systems with idempotency, backfills, and reconciliation.”

“Backend engineer with experience building an end-to-end civic tech AI platform that ingests city council meeting videos, transcribes them with Whisper, and enables natural-language Q&A via a LangChain/FAISS RAG pipeline. Demonstrated strong systems thinking by tuning retrieval for accuracy/latency/memory (cutting response time ~3s→1s and memory ~500MB→25MB) and by safely migrating an ERP from monolith toward services using dual writes, reconciliation, and idempotency to protect financial workflows.”

“Backend engineer from FoodSupply.ai who built and evolved a scalable restaurant/supplier product and order management platform using Node.js and REST APIs. Implemented a hybrid MySQL+MongoDB data architecture, optimized performance with Redis/Prisma, and led a phased migration with feature flags and a temporary sync layer to maintain data consistency. Strong focus on production security (OAuth2, RBAC, row-level security, AWS IAM) and reliability practices (testing with Pytest, Docker/AWS pipelines).”

“Early-career AI/LLM builder who created and deployed a multi-agent news analysis agent (Patrakarita) using CrewAI, coordinating researcher/analyst roles to turn noisy article URLs into structured, prioritized outputs (claims, tone, verification questions, opposing views). Strong focus on orchestration debugging and reliability evaluation, including measuring hallucination/redundancy and improving reasoning by refactoring pipeline sequencing.”

“Currently at ProShare and reports building an AI/LLM-powered system deployed to production, aimed at helping with status-related difficulties and reducing misunderstandings across transactions. Also cites prior collaboration at Porsche with marketing teams, focusing on translating marketing goals into technical requirements and communicating solutions clearly to non-technical stakeholders.”

“Built and production-deployed a Streamlit-based PDF RAG chatbot using LangChain (FAISS, embeddings, prompt templates) and OpenAI, optimizing Streamlit’s stateless behavior by caching vector DB + chat history to cut latency and API cost. Demonstrates a rigorous evaluation mindset (gold datasets, unit tests, LLM-as-judge, groundedness KPIs) and has experience communicating privacy/accuracy safeguards (RBAC, data masking, citations) to a non-technical client at Kalven Technologies.”