Vetted Retrieval-Augmented Generation (RAG) Professionals

“Backend/AI engineer with Johnson & Johnson experience building data-heavy payer/claims analytics services (Python/FastAPI, PostgreSQL, AWS) and optimizing them under peak ingestion load via indexing/query tuning and caching. Also shipped an end-to-end RAG feature for clinicians to extract insights from unstructured clinical notes, using constrained prompts and retrieval-confidence guardrails to prevent hallucinations.”

“AI software engineer with experience spanning LLM/RAG production systems and regulated fintech infrastructure. Built an end-to-end natural-language-to-SQL analytics assistant (Weaviate + GPT-4 + Supabase) shipped as an API with 92% accuracy and major time savings for non-technical users, and also owned demand-forecasting and CI/CD/containerization improvements for a Bank of America core banking deployment at Infosys.”

“Applied LLMs to high-stakes domains (wildfire risk for emergency teams and loan approval via a fine-tuned IBM Granite model), with a strong focus on reliability—using RAG-based cross-validation to reduce hallucinations and continuous ingestion pipelines (MODIS satellite imagery via AWS Lambda) to keep data current. Experienced in production orchestration and MLOps-style workflows using Airflow, AWS Step Functions, and SageMaker Pipelines, and collaborates closely with analysts on KPI-driven evaluation.”

“Backend engineer with hands-on experience building real-time, low-latency systems: owned the Python backend for a real-time crowd-monitoring product (top 5% at HackHarvard 2025) using OpenCV, GPU YOLO inference (PyTorch), WebRTC, and OAuth. Also has production Kubernetes/GitOps experience (Helm/Kustomize, GitHub Actions, Argo CD), Kafka-based event pipelines, and executed a minimal-downtime on-prem PostgreSQL migration to AWS EC2.”

“At onedata, built and deployed an LLM-powered, multi-agent analytics platform on AWS Bedrock that lets users create Amazon QuickSight dashboards through natural-language conversation, cutting dashboard build time from ~30 minutes to ~5 minutes. Strong in production concerns (observability, token/cost tracking, model tradeoffs) and in bridging business + technical work, owning pre-sales pitching through delivery with an engineering management background focused on AI product management.”

“Full-stack engineer who built "Workstream AI," an AI-powered engineering visibility product that converts GitHub activity into real-time insights using an event-driven microservices stack (RabbitMQ/Postgres/Express) and GPT-4 with a React frontend. Previously a Founding SWE at a health & wellness startup, building data-driven user management tooling, and also delivered a real-time shuttle tracking/ride request system using Java Spring Boot/Hibernate + React; comfortable owning production deployment details (AWS EC2, DNS, SSL).”

“ML/AI engineer with production experience in high-scale banking fraud detection at Truist, building an end-to-end pipeline (Airflow/AWS Glue/Snowflake, PyTorch/sklearn) with automated retraining and Kubernetes-based deployment; delivered measurable gains (22% fewer false positives, 15% higher recall) and reduced manual ops ~40%. Also partnered with clinicians at Kellton to deploy an LLM system for summarizing/classifying clinical notes, improving review time and decision speed.”

“Built production AI/RAG-style systems for message Q&A and insurance claims workflows, combining data ingestion, indexing/retrieval, and LLM integration with fallback modes. Has hands-on orchestration experience (Airflow, Prefect, LangChain) and cites large operational gains (claims processing reduced to ~45 seconds; manual review -50%; false alerts -30%) through automated, monitored pipelines and close collaboration with non-technical stakeholders.”

“AI/LLM engineer at Humana who built and deployed a HIPAA-aware RAG system for clinical record retrieval, cutting search time dramatically and improving retrieval efficiency by 30%. Experienced with Spark-scale data preprocessing, QLoRA fine-tuning, LangChain orchestration, and MLflow+SageMaker integration, with a strong testing/evaluation discipline (A/B tests, human eval) to hit 95%+ accuracy and production latency targets.”

“Backend/AI engineer in healthcare/insurance (mentions Cigna) who has shipped production systems spanning high-reliability APIs, async job architectures (Celery), and LLM/RAG features. Built an LLM document assistant with Terraform-managed AWS infra, semantic search retrieval, and strict permissioning/audit logs, and designed an automated prior-authorization workflow with human-in-the-loop escalation and compliance-driven thresholds.”

“Built a production LLM/RAG solution for healthcare operations teams to query large policy and care-guideline repositories in natural language. Improved domain alignment using vector retrieval plus parameter-efficient fine-tuning and prompt optimization, validated through internal user testing and metrics, cutting manual lookup time by ~40%. Also has hands-on experience orchestrating automated ML pipelines with Apache Airflow.”

“Built and deployed LLM-powered analytics and reporting systems, including a RAG-based assistant over Snowflake that let business users ask questions in plain English instead of writing SQL. Experienced orchestrating LLM agents (LangChain) and serverless reporting pipelines (AWS Lambda/S3/RDS), with a strong focus on grounded outputs, monitoring/evaluation, and data quality—used daily by non-technical finance and operations teams at Cigna.”

“Built and deployed a production Llama 3-based RAG document Q&A system using FAISS, addressing context-window limits through chunking and keeping retrieval accurate by regularly refreshing embeddings. Has hands-on orchestration experience with LangChain and LlamaIndex for multi-step LLM workflows (including memory management) and collaborates with non-technical teams (e.g., marketing) to deliver AI solutions like recommendation systems.”

“Full-stack engineer with cloud and GenAI experience who has owned production features end-to-end, including a reporting dashboard optimized from 14s to 5s using query/API refactoring and monitored via AWS CloudWatch. Also productionized an OpenAI-powered chatbot using LangChain with prompt design, guardrails, and evaluation via production logs and user feedback, and has led incremental legacy-to-microservices modernization with parallel run to avoid regressions.”

“At Delta Airlines, built and shipped a production LLM-powered semantic search/troubleshooting assistant over maintenance logs and operational documentation using OpenAI embeddings and a vector database. Implemented hybrid ranking, query enrichment, and structured filters to improve relevance ~35% while optimizing latency via caching and vector tuning. Also designed a scalable Kafka + AWS (Lambda/SQS) ingestion pipeline with strong reliability/observability and an eval loop using real engineer queries and human review.”

“Backend-leaning founding/early engineer who built automation platforms end-to-end: FastAPI/Python services integrated with a Next.js/TypeScript frontend, including a production VNC streaming URL endpoint for cloud-instance desktop viewing. Also designed core Postgres user/workflow data models and built an agentic orchestration system with LangChain/LangGraph (sub-agents, validators, pause/resume), plus made scalability tradeoffs like S3 pre-signed uploads to keep microservices responsive.”

“Backend/data engineer with experience at Assurant and Capgemini, focused on reliability and performance at scale. Improved high-latency backend APIs by adding and iterating on a Redis caching layer driven by CloudWatch/monitoring metrics, and built scalable BI pipelines that normalize messy multi-source enterprise data with strong observability and error handling. Familiar with LLM/RAG architecture and practical guardrails, though has not yet shipped an LLM feature to production.”

“Full-stack engineer who built an end-to-end low-code/no-code IDE for creating AI/ML workflows for industrial IoT sensors using Next.js/TypeScript and NestJS microservices. Focused on scaling high-volume sensor dashboards—improved UX and performance via WebSockets, debouncing, pagination, and API payload reduction—validated with profiling tools and user feedback in a startup environment.”

“Consulting-style LLM practitioner who builds enterprise knowledge assistants using RAG and takes them from prototype to production with guardrails, evaluation, and full-stack observability. Experienced partnering with IT and customer-facing teams to demo solutions, build tailored prototypes, and drive adoption through API-based integration.”

“Built and shipped AI-powered workflow automation at Oracle, including an MCP-based agentic workflow with tool-calling and guardrails, plus Grafana monitoring and Confluence documentation. Also led a Django monolith-to-microservices migration at Chamsmobile using blue-green deployment and load balancer traffic splitting to avoid regressions while modernizing production systems.”

“Hands-on AI/LLM practitioner who built a RAG-based customer support chatbot and tackled production issues like data chunking complexity and response-time lag. Uses techniques such as overlapping chunks, semantic search, context engineering, and query routing, and has experience presenting technical demos/workshops to developer audiences.”

“Full-stack engineer with strong production ownership: built and operated a real-time transaction monitoring/fraud-alerting system using Java Spring Boot, Kafka, Docker, and AWS with CI/CD. Demonstrates metrics-driven operations (latency, stability, consumer lag, true/false positives) and reliability patterns for integrations (idempotency, retries/backoff, DLQs, reconciliation/backfills), plus modern React/TypeScript + Node/Postgres architecture experience.”

“AI Backend Engineer in MetLife’s claims technology group who built and deployed a production LLM-based decision support system that helps claim adjusters quickly find relevant policy rules from long PDFs and historical notes. Designed it as multiple production-grade services with retrieval-first guardrails, continuous validation, and Airflow-orchestrated pipelines for ingestion, embeddings, and vector index updates to keep the system reliable as policies and data evolve.”