Vetted Retrieval-Augmented Generation Professionals

“Built and deployed a production RAG-based document Q&A system on Azure OpenAI to help business teams search thousands of PDFs/Word files, using Qdrant vector search, MongoDB, and a Flask API. Demonstrates strong production engineering (streaming large-file ingestion, parallel preprocessing, monitoring/retries) plus systematic prompt/embedding/chunking experimentation to improve accuracy and reduce hallucinations, and has hands-on orchestration experience with ADF/Airflow/Databricks/Synapse.”

“ML/NLP engineer who built a RAG-based technical assistant for Caterpillar field engineers, transforming PDF keyword search into intent-based semantic retrieval across manuals, logs, sensor reports, and technician notes. Strong in productionizing data/ML systems (Airflow, PySpark) with rigorous preprocessing, entity resolution, and evaluation—delivering measurable gains in accuracy, relevance, and duplicate reduction.”

“Built and deployed a production LLM system that scraped Google Maps menu photos, extracted structured prices via OpenAI, and cross-validated them against website-scraped data to automate data-quality verification at scale (replacing costly manual contractor checks). Demonstrates strong reliability instincts—precision-first prompting, output gating with image-quality metadata, and fuzzy matching/RAG techniques—plus solid orchestration (Dagster/Airflow) and observability (Sentry, Prometheus/Grafana).”

“ML/NLP practitioner at Morf Health focused on unifying fragmented healthcare data by linking structured patient/encounter records with unstructured clinical notes. Has hands-on experience with transformer embeddings, vector databases, and domain fine-tuning, plus rigorous evaluation (precision/recall) and human-in-the-loop validation with clinical SMEs to make pipelines production-grade.”

“Customer-support/engineering background spanning Informatica PowerCenter ETL and IBM demos/workshops, with hands-on experience hardening data workflows for production (error tables/reject links, validation, restart strategies, alerting, performance tuning). Also demonstrates a clear, systems-level approach to diagnosing LLM/agentic workflow issues (prompt/RAG/tooling/memory) using instrumentation and iterative fixes, and has partnered with sales on POCs by defining success metrics and mapping solutions to customer architectures.”

“Backend engineer on Morgan Stanley’s trade risk and compliance platform, building Java/Spring Boot microservices that validate equity and fixed-income trades at multi-million-events/day scale. Shipped an LLM-assisted trade exception analysis feature using RAG over internal policy documents and trade history, with production-grade guardrails (confidence thresholds, audit logs, human-in-the-loop) and measurable performance wins (~30–35% faster reporting) through PostgreSQL tuning and Redis caching.”

“AI/ML engineer at Cigna Healthcare building a production, HIPAA-compliant LLM-powered clinical insights platform that summarizes unstructured medical notes using a fine-tuned transformer + RAG on AWS. Demonstrates strong end-to-end MLOps and cloud optimization (distillation, Spot/Lambda/Auto Scaling) with quantified outcomes (~28% accuracy lift, ~40% less manual review, ~25% lower ops cost) and strong clinician-facing explainability via SHAP and dashboards.”

“Currently at Huntington Bank, built a production-grade RAG system that helps business/operations teams get grounded answers from large volumes of internal enterprise documents. Owns ingestion and FastAPI backend, tuned hybrid BM25+vector retrieval and chunking for relevance, and evaluates reliability with metrics and observability (LangSmith, CloudWatch, Prometheus/Grafana) while partnering closely with non-technical stakeholders.”

“Built Nexthire-AI, shipping an end-to-end LLM-powered resume–job description matching product (React + Node.js) using embeddings and retrieval to generate match scores and skill-gap recommendations. Improved post-launch engagement by making feedback cleaner and more actionable, and added production guardrails (validation, timeouts, fallbacks) to handle messy resume formats and AI API instability.”

“Full-stack engineer with fintech trading-platform experience who shipped and operated a real-time portfolio P&L/performance feature end-to-end (React + Node/WebSockets + MongoDB) on AWS, including significant performance tuning under peak trading load. Also built a Spark-based trading analytics pipeline with idempotency and reconciliation for auditability, and has a personal React/TS + Node/Express project (Artsy) with JWT auth and schema-evolution practices.”

“Backend/platform engineer who has built and scaled production Java/Spring Boot + Kafka services on AWS/Kubernetes (1M+ msgs/day) and led reliability/performance fixes that restored SLAs (25–30% latency improvement; 99.9% uptime). Also shipped an AI customer-support chatbot end-to-end using retrieval + guardrails and rigorous evaluation/observability, improving resolution time 40% and satisfaction 25%, with a strong plan/execute/verify approach to agentic workflow reliability.”

“Full-stack engineer who shipped an end-to-end speech capability for an LLM chatbot UI, integrating OpenAI APIs and publishing via Google Apigee with client documentation. Has experience operating deployments with Jenkins/Kubernetes/Docker and monitoring with Datadog, and has worked in an innovation-center environment building rapid prototypes under ambiguity with tight stakeholder feedback loops.”

“Verizon engineer who productionized an LLM-based personalization capability for a customer-facing digital platform, owning the path from success metrics through scalable APIs, A/B validation, and post-launch monitoring (latency/accuracy/drift). Experienced in diagnosing and fixing real-time LLM/RAG workflow issues under peak load, and in enabling adoption via tailored technical demos/workshops and sales support materials.”

“Software engineer with a CS/Computer Engineering background who has worked on ML/NLP (Hugging Face, clinical NLP, text generation and structured extraction) and has a school robotics project integrating a trained ML model with microprocessor-controlled hardware to drive motor movement and writing. Currently focused on building and deploying applications and ML models to AWS/Azure using Docker, Kubernetes, and CI/CD; targeting ~$150K compensation.”

“Built and led an autonomous driving software effort for Formula Student, owning the full autonomy stack (perception, planning, control) orchestrated in ROS. Implemented stereo depth + YOLO object detection, RRT/RRT* planning, and a robust SLAM pipeline (Kalman filter, submapping) while leveraging Gazebo simulation and modern deployment tooling (Docker/Kubernetes, AWS, GitHub Actions CI/CD).”

“Robotics engineer with Honeywell and Tata Motors experience deploying ROS/ROS2 autonomous mobile robot fleets into live factory environments, integrating sensors, safety PLCs, and on-prem services. Known for solving end-to-end latency and stability issues (including network spikes under load) using gRPC, Docker, and improved diagnostics—cutting diagnosis time from hours to minutes and achieving sub-150 ms control response.”

“Built and deployed a fine-tuned Qwen 2.5 14B model into production at Dextr.ai as the backbone for hotel-operations agentic workflows, running on AWS EKS with Triton and TensorRT-LLM. Demonstrates strong cost-aware LLM engineering (QLoRA, FP8/BF16 on H100) plus rigorous benchmarking/observability (Prometheus, LangSmith) with reported sub-30ms TTNT. Previously handled long-running ETL orchestration with Airflow at GE Healthcare and Lowe's.”

“Built and deployed a production LLM-powered lesson adaptation platform for K–12 educators that personalizes content for multilingual and neurodiverse students using RAG and content transformation. Owned the full stack from FastAPI backend and OpenAI integration through reliability/safety controls, latency/cost optimization, and weekly shippable modular APIs, iterating directly with curriculum stakeholders to reduce hallucinations and improve educator trust.”

“GenAI/ML engineer from Deloitte who built and shipped a production RAG-based internal search assistant for support teams, delivering quantified operational gains (20% effort reduction, 35% faster manual lookup). Experienced in enterprise-grade LLM reliability (grounding/hallucination control), compliance/security constraints, and rapid release cycles using CI/CD, MLflow, and orchestration tools (Airflow, Databricks Jobs, LangChain).”

“LLM/RAG engineer with production deployments in highly regulated domains (Frost Bank and GE Healthcare). Built secure, explainable document-grounded Q&A systems using LoRA fine-tuning, strict RAG with confidence thresholds, and citation-based responses; also established evaluation/monitoring (golden QA sets, hallucination tracking, drift) and achieved ~40% latency reduction through retrieval/prompt tuning.”

“LLM/RAG engineer who took a PDF-heavy agent from prototype to production for an Africa-based client, combining Pinecone retrieval with robust PDF parsing (unstructured.io, OCR, structured table extraction). Demonstrates strong production mindset (eval metrics, prompt hardening, security/scalability) and measurable optimization impact (30% efficiency gain, 2x faster responses), and has helped close deals by building security-focused POCs for skeptical IT stakeholders.”

“ServiceNow engineer who built an AI-powered ticket summarizer end-to-end (RAG with vector DB + GPT, Redis latency optimizations, fallback summarization, and a React UI widget for agent feedback). Also has hands-on ROS 2 experience building real-time sensor-fusion nodes (LiDAR/IMU), debugging SLAM/navigation issues via rosbag + EKF tuning, and bridging heterogeneous robots by translating ROS 2 topics to MQTT/JSON. Strong DevOps background with Docker, Jenkins CI/CD, and Kubernetes orchestration for scalable deployments.”

“Built a production AI-driven contract/document extraction system combining OCR, normalization, and LLM schema-guided extraction, orchestrated with PySpark and Azure Data Factory and loaded into PostgreSQL for analytics. Emphasizes reliability at scale—using strict JSON schemas, confidence scoring, targeted retries, and multi-layer validation to control hallucinations while processing thousands of PDFs per hour—and partners closely with non-technical business teams to refine fields and deliver usable dashboards.”

“Built and productionized a HIPAA-compliant LLM+RAG Clinical AI assistant at Optum, fine-tuning GPT/LLaMA on de-identified patient notes and integrating FAISS/Pinecone for sub-second retrieval; reported to cut diagnosis time by ~20 minutes per case. Experienced in orchestrating ML pipelines (Airflow, AWS Step Functions, Azure Data Factory) and in reliability techniques for LLM systems (grounding, citations, confidence filters, monitoring) while partnering closely with clinicians and compliance teams.”