Vetted Retrieval-Augmented Generation (RAG) Professionals

“Built and deployed a production long-form article summarization system using BART/T5/PEGASUS, tackling real-world constraints like token limits, latency/quality tradeoffs, and factual drift via chunking/merge logic and constrained decoding. Uses pragmatic Python-based pipeline orchestration (scheduled jobs, modular scripts, logging/retries) and iterates with stakeholder feedback to make outputs genuinely useful for content workflows.”

“LLM/ML platform engineer with hands-on experience taking an LLM document summarization prototype into a production-grade service on AWS EKS, emphasizing low-latency inference, drift monitoring, and safe CI/CD rollouts (canary + rollback). Strong in real-time debugging of agentic/RAG systems (tracing, retrieval/index drift fixes) and in developer enablement through practical workshops (Docker/Kubernetes/FastAPI) plus pre-sales support via demos and benchmarks to close pilots.”

“Founding AI engineer (June 2024) at Talon Labs who built and productionized an LLM-powered chatbot for interacting with proprietary supply-chain documents, deployed at large scale (25–100,000 users). Experienced with RAG/LLM orchestration (LangChain, LlamaIndex, Groq AI) and production ops tooling (Kubernetes, Docker, Kubeflow, Airflow), with a metrics-driven approach to evaluation, observability, and stakeholder alignment.”

“Product-focused full-stack engineer (70/30 app vs infra) with Accenture experience and recent AI workflow work, shipping end-to-end systems from React/TypeScript UIs through FastAPI backends to Postgres. Built an AI-driven data extraction platform with async job APIs, strict schema validation, and strong observability, and has operated AWS ECS-based deployments with real incident mitigation (DB connection exhaustion/latency under traffic spikes).”

“Engineering leader who stays hands-on in high-leverage technical areas (architecture, scalability, reliability) while operating at an executive level. Led StagePilot’s shift from a tightly coupled legacy system to a cloud-native, event-driven real-time platform proven at 1M+ concurrent users, and previously scaled multiple SRE teams at McGraw-Hill with SLOs, on-call, and blameless ops practices.”

“Finance-domain ML/LLM engineer who has shipped production systems including a RAG-based financial insights assistant with a custom post-generation validation layer that verifies atomic claims against retrieved source text to prevent hallucinations in compliance-critical workflows. Also built large-scale MLOps automation on AWS using Kubeflow + MLflow + CI/CD for fraud detection and credit risk models processing 500M+ transactions/day with a 99.99% uptime goal, and partnered closely with JP Morgan risk/compliance stakeholders on NLP-driven compliance monitoring.”

“Robotics-focused engineer with co-op experience building and debugging embedded C++/Python drivers for time-of-flight sensing on a Flex Stacker product, plus automation of large-scale test data collection via Google Drive/Sheets APIs to enable parallel robot testing. Also has ROS2 sensor-driver experience (GPS/RTK/IMU with custom messages/ROSbags) and is building a side project integrating Whisper-based live transcription with chunked abstractive summarization in a latency-aware pipeline.”

“LLM/GenAI engineer with US Bank experience building a production financial-document intelligence platform using LangChain/LangGraph, GPT-4, and Amazon OpenSearch. Delivered a RAG-based assistant for compliance/audit teams with grounded, cited answers, focusing on reducing hallucinations and latency, and deployed securely on AWS (SageMaker/EKS) with CI/CD and evaluation tooling (LangSmith, RAGAS).”

“Built and deployed a production LLM-powered clinical insights/summarization assistant for healthcare teams, including a Spark+Airflow pipeline, fine-tuned transformer models, and a FastAPI Docker service on AWS. Demonstrates strong MLOps/LLMOps depth (Airflow on Kubernetes, custom AWS operators/IAM, MLflow, CloudWatch) and practical reliability work like hallucination mitigation, confidence scoring, and retrieval-backed evaluation with shadow deployments.”

“Backend/AI workflow engineer with experience at AirKitchenz, Uber, and Vivma Software, building production systems on AWS (Lambda, DynamoDB, Step Functions). Has a track record of major performance wins (DynamoDB latency 2s to <150ms; Postgres query 2s to ~180ms) and shipping LLM-powered onboarding and ticket-routing workflows with strong guardrails (schema validation, confidence thresholds, human-in-the-loop escalation).”

“Currently working in CoRAL Lab, built and deployed IntegrityShield—a document-layer PDF watermarking system that keeps assessments visually identical while disrupting LLM-based solving; validated in a real classroom where it helped catch 12 AI-cheating cases. Also built MALDOC, a modular red-teaming platform for document-processing AI agents using LangGraph to run reproducible, deterministic adversarial trials across OCR/text/vision routes.”

“Full-stack Java engineer (4+ years) who led end-to-end modernization of high-latency order management systems into cloud-native reactive microservices (Spring WebFlux) and built real-time React/Redux dashboards, reporting 99.98% uptime and 22% infra cost savings. Also headed a production RAG-based Order Support Bot at Dell Technologies with embeddings + MongoDB semantic search, automated validation and human fallback, plus CI/CD-driven LLM eval loops to reduce hallucinations.”

“Built and deployed a production RAG-based internal knowledge assistant that let analysts query company documents in natural language, using LangChain/LangGraph with Pinecone and a FastAPI service for integration. Emphasizes reliability in production through hallucination mitigation (retrieval tuning + prompt guardrails) and measurable evaluation/monitoring (accuracy, latency, task completion, hallucination rate), iterating based on user feedback.”

“Backend/DevOps engineer pivoting into robotics/space, building hands-on ROS2 (Humble) skills via Gazebo simulations and experimenting with Nav2 and slam_toolbox. Brings strong distributed-systems and real-time debugging practices (profiling, instrumentation, QoS/retry patterns) and is actively learning perception and control fundamentals to transition into autonomous robotics.”

“Internship experience at Qualitest building and deploying an LLM-powered test automation system that reduced manual test creation and improved efficiency (~40%). Demonstrates strong production engineering for LLM systems (timeouts/retries/monitoring/caching, prompt optimization, batching) and has scaled workflows to 100+ concurrent jobs; also has orchestration experience with AWS Step Functions and Kubernetes.”

“Customer-facing technical professional with experience supporting LLM/agentic-style workflows and complex integrated systems (APIs, backend logic, databases). Partnered with sales/customer teams at Radix Health to onboard new clients in phased prototypes, translating non-technical requirements into technical scope and implementing core product changes to tailor the appointment-booking solution for providers.”

“GenAI/ML engineer (CitiusTech) who has deployed production RAG systems for compliance/operations document Q&A, using Pinecone + FastAPI microservices on Kubernetes with strong monitoring and guardrails. Also built a GenAI-powered incident triage/routing solution in collaboration with non-technical stakeholders, achieving 35% faster response times and 40% fewer misclassified tickets, and has hands-on orchestration experience with Airflow and AutoSys.”

“At Inertia Systems, built a production LLM-powered ingestion pipeline that converts heterogeneous sources (PDF/JSON/IFC/SQL and financial tables) into standardized text and uses GraphRAG to construct a knowledge graph with verified dependency relationships. Also has hands-on HPC orchestration experience with SLURM, including creating a custom wrapper process manager to improve resource utilization under restrictive scheduling policies.”

“Open-source JavaScript contributor focused on performance and maintainability in data visualization libraries—refactored legacy ES5 into modular ES6, added tests/docs, and delivered ~30% faster load times with positive community adoption. Also optimized a React dashboard (~40% load-time reduction) and took ownership in an ambiguous AI product initiative by setting milestones, standing up an initial ML pipeline, and shipping a prototype in ~6 weeks that became the basis for production.”

“Built and deployed a production RAG-based conversational "Yelp for AI tools" at Search-AI Inc., focused on personalized, explainable AI tool recommendations from thousands of options. Emphasizes production-grade reliability and performance (hybrid retrieval, async two-stage pipelines) and is also building a multi-agent orchestration layer (MAgIc) with typed memory and controlled coordination policies.”

“Built a production-oriented multimodal RAG "Fix Assistant" with FastAPI, Tavily search, BM25 + cross-encoder reranking, and a local Phi-3.5 model, emphasizing strict grounding and fallback/verification modes to prevent hallucinations. Also has hands-on federated learning experience using STADLE to orchestrate edge-node training and aggregation for EV telemetry data, plus experience communicating AI results to non-technical stakeholders (traffic RL/congestion outcomes).”

“Built and deployed a production LLM-powered biomedical knowledge extraction pipeline that processed millions of papers to identify tools/techniques and produce a unified knowledge graph via active learning NER (Prodigy + spaCy transformers) and entity linking (Bio-tools/Wikidata). Addressed hard NLP engineering challenges like WordPiece span-offset alignment and scaled inference over ~1.5M documents using batching/caching, containerized services, async workers, and orchestration with Prefect/Airflow.”

“Built and deployed LLM-powered agentic systems including a multi-agent travel planning assistant using LangChain, RAG (FAISS), real-time APIs, and a supervisor agent to manage coordination and reduce hallucinations. Also developed a Text-to-SQL system with schema-aware validation guardrails, and collaborated with drilling domain experts at CNPC USA to build an ML model predicting rate of penetration (ROP).”

“Small-team builder of Promethium’s “Mantra” next-gen agentic text-to-SQL engine, using vector DB + LangGraph tooling and SQL validation/evaluation to improve query accuracy. Experienced in diagnosing production LLM workflow failures via LangSmith traces and in running hands-on developer workshops and pre-sales POCs with live debugging and real customer data.”