Vetted Retrieval-Augmented Generation (RAG) Professionals

John Chance

Screened

Senior Machine Learning Engineer specializing in conversational AI and healthcare ML

Greenwood, LA9y exp

“ML/AI engineer with hands-on ownership of both classical recommender systems and safety-sensitive LLM agent platforms. They combine production MLOps depth with behavioral health domain experience, including clinical safety validation, explainability, and multi-agent orchestration, and cite measurable impact in both business metrics and latency reduction.”

“GenAI/ML engineer with hands-on experience building production financial intelligence and document summarization systems at Citibank. Stands out for combining LLM fine-tuning, hybrid RAG, multi-agent workflows, and strong MLOps/observability practices to deliver measurable business impact, including 60% faster analyst retrieval, 31% higher precision, and 99%+ uptime.”

“ML/AI engineer with hands-on experience building production systems in financial services, including a real-time underwriting analytics platform at Hartford Financial Services. Stands out for combining classic ML, low-latency API deployment, monitoring, and emerging LLM/RAG design patterns, with measurable impact including 20% better decision accuracy, sub-200ms latency, and 5M+ records processed daily.”

kartikeya tiwari

Screened

Senior Software Engineer specializing in AI systems and platform engineering

Bangalore, India6y exp

“Backend/AI engineer with experience owning production systems in fintech and product startups, including a predictive scaling platform that cut AWS spend by 40% and an ambiguous social-intelligence feature that doubled MRR from $50K to $100K. Also building AI search and document-processing workflows, with reported 99.7% extraction accuracy and hands-on use of both classical forecasting and modern LLM stacks.”

“Backend-focused engineer with experience at Charles Schwab owning financial workflow deployments end-to-end, including API/database design, SQL optimization, Python automation, and AWS-based production stabilization. Also brings applied AI quality experience through building LLM/agent validation pipelines focused on scenario testing, edge-case detection, and reducing production risk.”

“Software engineer currently building AI-powered backend systems for interview analysis, with end-to-end ownership of an LLM-based monitoring platform. Stands out for combining practical product delivery in an ambiguous early-stage environment with measurable impact: over 40% reduction in manual review effort and roughly 20% lower inference cost.”

“AI-native software developer who has built a highly structured workflow around Claude, Cursor, design agents, and SpecKit to plan, design, implement, and test features end to end. They also use multi-agent setups with sub-agents and git worktrees, and have experience acting as a tech lead for AI agents by assigning roles, guiding execution, and reviewing outputs.”

Jeffrey Ren

Screened

Mid-level Full-Stack Software Engineer specializing in SaaS and AI-enabled web applications

Henderson, NV5y exp

“Full-stack engineer who led an end-to-end rebuild of a service-agent case management app (React SPA + backend/DB updates) and added Datadog monitoring, improving agent throughput by ~1 case/hour and saving roughly $15K/month. Experienced in incremental legacy modernization (including moving a legacy React frontend toward a Rails-based approach) with heavy unit/E2E testing and strong cross-team stakeholder communication.”

Koushik Ravikumar

Screened

Mid-level Full-Stack Engineer specializing in cloud-native Java and AI platforms

Kyle, TX4y exp

“Full-stack engineer with strong cloud and platform experience spanning React, Go, AWS, Kafka, and Terraform. Has led complex migrations from monolithic/containerized systems to microservices and cloud deployments, built compliance-oriented logging infrastructure, and improved a broken frontend codebase to achieve a 3x performance gain while making it easier for other developers to extend.”

“Built end-to-end product features spanning full-stack web development and LLM-powered systems in an early-stage startup environment. Notably shipped an AI financial assistant chatbot with agent routing, validation, fallback handling, and production monitoring, and also owned a scheduling system integrating Next.js, backend APIs, database design, and Google Calendar OAuth.”

“AI product engineer with hands-on experience shipping enterprise LLM systems at General Motors, including NL2SQL analytics, RAG-based enterprise search, and multi-agent document analysis. Stands out for combining strong technical depth in LangChain/Vertex AI/Pinecone/Redshift with disciplined evals, human-in-the-loop design, and clear business impact such as 70% to 90%+ accuracy gains, 3x analyst throughput, and rapid MVP delivery in 6 weeks.”

Yujun Liu

Screened

Junior AI software engineer specializing in agentic workflows and cloud platforms

Cambridge, MA3y exp

“AI/full-stack builder who has owned end-to-end LLM features in both creative tooling and education workflows. Built a multi-agent film-production workspace for Backlot and an automated ingestion pipeline at iOffer.AI that cut counselor manual entry by 70%, with hands-on depth in orchestration, validation, monitoring, and human-in-the-loop system design.”

“Full-stack engineer with 8 years of experience spanning regulated healthcare IoT and enterprise security SaaS. Has worked on a high-growth healthcare equipment platform and DigiCert's certificate lifecycle management product, combining hands-on React/Node.js development with compliance, auditability, and reliability requirements. Currently seeking a more code-heavy role after moving into a more advisory position.”

Omkar Tulsidas Parab

Screened

Mid-level Software Engineer specializing in full-stack web and AI applications

United States5y exp

“Software engineer who owned an Order Management System end-to-end at Reliance Jio, improving large-table performance via UI virtualization shipped behind feature flags and refined through direct ops-user observation. Also built an OCR automation tool at Piramal Realty using Python/Tesseract with validation and manual correction fallbacks, driving adoption by operations teams. Experienced integrating with Kafka-based microservices and improving observability using structured logging and correlation IDs.”

“Yogesh is an AI/full-stack engineer from LangChain who says he was the sole developer and core maintainer of OpenSWE/OpenSpeed, an asynchronous coding agent in LangSmith Cloud that turns requests from Slack, Linear, and GitHub into reviewable PRs. He emphasizes production-grade agent infrastructure: event-driven workflow design, typed run states, observability, retries, and latency improvements via pre-warmed sandboxes.”

“Full-stack TypeScript engineer with hands-on experience building e-commerce and subscription/dashboard features across React, Node.js/Express, MongoDB, and PostgreSQL. Has owned features through AWS/GitHub Actions deployment and post-production support, including diagnosing stale-cache issues in production and improving team velocity by standardizing reusable UI components.”

“AI/LLM engineer who built a production intelligent support system using RAG over a vectorized documentation library, addressing real-world issues like lost-in-the-middle context failures and doc freshness via automated GitHub-driven re-embedding pipelines. Emphasizes rigorous agent evaluation (component/E2E/ops) and prefers lightweight, decoupled workflow automation using message brokers (Redis/RabbitMQ) over heavyweight orchestration frameworks.”

“Built a production multi-agent orchestration platform to automate healthcare claims and HR workflows, combining LangChain/CrewAI/AutoGPT with RAG (FAISS/Pinecone) and fine-tuned open-source LLMs (LLaMA/Mistral/Falcon) in private Azure ML environments to meet HIPAA requirements. Emphasizes rigorous agent evaluation/observability (trajectory eval, adversarial testing, LLM-as-judge, drift monitoring) and reports measurable outcomes including 35% faster claims processing and 40% fewer chatbot errors.”

“Has production deployment experience delivering computer-vision systems on AWS (Docker + S3) including a GDPR-focused face/license-plate obfuscation pipeline and a semantic-segmentation project aimed at reducing annotation time. Worked closely with DevOps and frontend teams and partnered with CEO/CMO to present an AI-driven annotation workflow to non-technical VC stakeholders.”

“Telecom (Verizon) AI/ML practitioner who built a production multimodal system that ingests messy customer issue reports (calls, chats, emails, screenshots, videos) and turns them into confidence-scored incident summaries with reproducible steps and evidence links. Also built KPI/alarm-to-ticket correlation to rank likely root-cause domains (RAN/Core/Transport), cutting triage from hours to minutes and improving MTTR.”

“AI/ML engineer with forensic analytics and healthcare claims experience (Optum), building production LLM/RAG systems to surface context-driven fraud patterns from unstructured claim notes and explain risk to investigators. Strong in large-scale retrieval performance tuning, legacy API integration with reliability patterns (SQS, circuit breakers), and MLOps orchestration on Airflow/Kubernetes with rigorous testing, monitoring, and stakeholder-friendly interpretability.”

“IBM engineer who built and deployed a production RAG-based LLM assistant using LangChain/FAISS with a fine-tuned LLaMA model, served via FastAPI microservices on Kubernetes, achieving 99%+ uptime. Demonstrates strong practical expertise in reducing hallucinations (semantic chunking + metadata-driven retrieval) and managing latency, plus mature MLOps practices (Airflow/dbt pipelines, MLflow tracking, monitoring, A/B and shadow deployments) and effective collaboration with non-technical stakeholders.”

“Robotics/AI candidate who built an AI-driven landmark location tool during a summer internship at Mobile Drive, combining YOLOv5 object detection with OpenStreetMap-based geolocation to handle dense, cluttered urban environments. Also researched deploying LLM-based agents on constrained hardware using quantization plus LoRA/continuous learning, improving accuracy from ~80% to ~92%, with an emphasis on production logging for reliability.”