Vetted ETL Professionals

“Built and productionized a MediCloud/Medicoud LLM microservice platform that lets clinicians query medical data in natural language, orchestrating multi-step RAG-style workflows with LangChain and evaluating/debugging with LangSmith. Delivered measurable gains (consistency ~70%→90% / +20%; latency ~2.0s→1.1s / -40%) by implementing structured prompts, fallback logic across multiple LLMs, hybrid retrieval tuning, and AWS Lambda performance optimizations (package size, async, caching).”

“Data/AI practitioner who built a production LLM-driven healthcare claims analytics and dashboarding system to reduce avoidable ER visits—processing 1.4M+ claims, flagging 19% as non-emergent, and projecting ~$2.8M in annual savings. Demonstrates strong real-world LLM reliability and performance engineering (grounding, numeric validation, caching, materialized views, quantization) plus orchestration experience with Airflow and Azure Data Factory.”

“Frontend engineer who led the end-to-end UI for a virtual trivia/multiplayer game, including architecture (component-driven + design system), quality practices (TypeScript, linting/formatting, unit + E2E tests), and real-time synchronization for ~100 concurrent players using Pusher. Emphasizes pixel-perfect, mobile-first responsive delivery with Tailwind and design tokens, plus ongoing refactors for reusability and performance.”

“Built a production LLM fine-tuning pipeline for domain-specific code generation at Pigeonbyte Technologies, including automated collection and rigorous quality filtering of 10M+ code samples (AST validation, sandbox execution/testing, deduplication, drift monitoring, and human-in-the-loop review). Also implemented end-to-end ML orchestration in Apache Airflow with data quality gates, dataset versioning in S3, benchmarking, and automated model promotion, and has a reliability-first approach to agent/workflow design.”

“Built and owned end-to-end systems for the Department of Water Resources and NAHC, including a debt infrastructure management system and a TypeScript/React + .NET 6 CMS. Strong in shipping quickly with quality (CI/CD, automated testing), optimizing SQL Server performance for large datasets, and implementing microservices-style async processing with reliability patterns (retries/idempotency/monitoring). Also delivered widely adopted internal workflow automation and reporting using Power Automate and Power BI.”

“Early engineering hire at The Coaching Market (B2B2C e-learning startup) who owned re-engineering core REST APIs (FastAPI) and shipping an enhanced Next.js UI, plus automating most deployments via CircleCI/Vercel. Strong in data-driven iteration (surveys/Jira/Slack + Google Analytics, A/B tests) and reliability/performance improvements with measurable impact (30% less downtime, 40% faster releases, 25% faster loads).”

“Backend/ML engineer with deep fintech and marketplace experience: built a real-time financial analytics + algorithmic trading platform (Python/Postgres/Kafka/Redis) and drove major DB performance wins (10x faster analytics; sub-10ms response consistency). Also shipped an end-to-end ML recruitment matching platform (scraping/ETL/modeling/Django deployment) with reported 92% matching accuracy, and emphasizes production reliability via monitoring, blue-green deploys, and robust workflow error handling.”

“Backend/data engineer with hands-on production experience building a FastAPI Python service on AWS for real-time AI workflows (Postgres/Redis, containers behind API Gateway) with strong reliability practices (JWT auth, timeouts/retries, health checks). Has delivered AWS infrastructure using Terraform + GitHub Actions across environments, built Glue ETL pipelines into Snowflake with idempotent recovery, and modernized legacy batch workflows via parallel-run parity validation and phased cutovers.”

“AI/ML practitioner with production experience building a RAG-powered contextual customer support agent, optimizing for low latency using vector databases and smaller LLMs. Also deployed a fraud detection model on Kubernetes with auto-scaling for heavy transactional loads, and improved chatbot accuracy by 15% through metric-driven testing and evaluation. Partners with Marketing on personalization/recommendation initiatives with measurable outcomes tied to customer feedback.”