Vetted Retrieval-Augmented Generation (RAG) Professionals

“Full-stack AI engineer who has built and deployed multiple end-to-end LLM products, including an AI interview assistant, a multi-agent market research platform, and a policy document explainer. Particularly strong in productionizing agentic workflows, integrating tools like Whisper, Tavus, LiveKit, CrewAI, and LangGraph, and hardening messy real-world AI/document pipelines with validation, memory isolation, and fallback handling.”

Muhammad Usman

Screened

Mid-level Full-Stack Engineer specializing in SaaS, AI, and Healthcare IT

Gulberg, Pakistan6y exp

“Fullstack engineer with roughly 3 years of experience who has independently built customer-facing systems in healthcare, including invoice notification infrastructure, nurse speech-to-text documentation, and a voice agent/chatbot workflow. Particularly interesting for teams needing hands-on builders who can ship end-to-end products with reliability features, real-time communication flows, and direct user-informed design.”

“Full-stack product engineer who has shipped AI-powered job board moderation and validation features end to end across React/TypeScript, serverless backends, and Postgres. Stands out for combining UX polish, LLM-backed workflow design, and reusable async infrastructure patterns to improve reliability, speed of delivery, and user participation.”

“Built and shipped a production "Campaign AI" multi-agent system (LangGraph) that personalizes B2B outbound emails at scale using Apollo.io prospect data, clustering-based segmentation, and 21 persona variants. Notably uncovered that high click rates were largely email security scanners and created a validated bot-detection/scoring pipeline (timestamps/IP/user-agent/click patterns), bringing reported engagement down from ~40% to a trusted 5–8% that aligned with real conversions.”

“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.”

Harshit Vashisth

Screened

Junior AI Engineer specializing in LLMs, RAG systems, and MLOps

Remote, United States1y exp

“Robotics software engineer who built an end-to-end system ("justmatrix"), focusing on multi-agent orchestration and a multi-RAG retrieval backend/API. Has hands-on ROS experience, including a custom node for reliable high-frequency sensor data routing, plus deployment automation using Docker, Kubernetes, and CI/CD.”

“Built and scaled an internal AI code-search/assistant agent that expanded from engineering-only to broader internal users, tackling legacy code and inconsistent standards to make a RAG pipeline production-ready. Uses a metrics-driven approach (user feedback + automated Python evaluation for retrieval relevance and latency) and has handled high-pressure outages, including moving parts of the stack off AWS and adopting Milvus on internal infrastructure for resilience.”

Tejaswi devarapalli

Screened

Junior Software Engineer specializing in backend systems and AI infrastructure

Los Angeles, CA2y exp

“Built both a full-stack AWS file-processing pipeline and a production AI document Q&A system ('smart-doc'). Stands out for combining strong cloud engineering with practical LLM/RAG architecture, including hybrid retrieval, reranking, structured outputs, confidence-based retries, and production monitoring.”

“Fullstack engineer with a strong serverless/AWS and applied AI profile, having built document-upload-to-RAG chatbot systems using Bedrock/Titan as well as a production fintech reporting platform. Particularly compelling for teams needing a zero-to-one builder who can own architecture, frontend, backend, and user-informed product delivery; one recent product reached 100+ student users within 48 hours of launch.”

“Frontend-focused candidate with hands-on experience building a technically demanding AI-assisted survey/copilot interface at VSorts.ai while working as a research assistant at ODU. They show strong practical judgment around React architecture, TypeScript safety, and performance tuning, including diagnosing context-driven re-render issues and improving UX in real-time interactive applications.”

“Backend-focused full-stack engineer with strong React/TypeScript depth who has owned end-to-end features spanning PostgreSQL, .NET 8 APIs, real-time React dashboards, and production monitoring. Notably built a geofencing tracking module for construction SaaS and a 0→1 secure LAN file transfer engine, combining security-first architecture with measurable outcomes like 40% lower battery usage and zero security breaches in pilot.”

“Solo builder of two technically ambitious products: Ghosted, a full-stack job search platform for international candidates navigating H-1B sponsorship data, and ContextForge, a Claude Code marketplace plugin that gives coding agents persistent memory and targeted codebase retrieval. Particularly strong in AI agent infrastructure, retrieval reliability, and end-to-end product ownership, with a fast release cadence and a habit of turning real failure modes into shipped improvements.”

“Hands-on automation and QA-focused developer using AI agents, MCP tools, and LLMs to streamline business workflows. Built agents for automated Jira bug logging, executive summary dashboards, and a rule-explainer that translates technical business rules into plain language for end users, while also supporting Selenium-to-Playwright migration and guiding peers on AI implementation.”

Muhammad Midhat

Screened

Senior Full-Stack/Backend Engineer specializing in APIs, distributed systems, and AI integrations

9y exp

“AI/backend engineer who has built and scaled production LLM-powered SaaS features (document assistant + compliance review agent) on a Node.js/TypeScript + Postgres/Redis stack deployed to GCP Kubernetes. Demonstrates strong production reliability chops—async queueing, autoscaling, observability, and database tuning—with quantified wins (p95 latency -60%, query 4s to <200ms) and robust AI guardrails (strict RAG, schema validation, citations, HITL).”

“Analytics and automation candidate with experience delivering data and AI solutions for major public-sector and enterprise clients including STC, Abu Dhabi Ports, and the Ministry of Culture. They combine SQL, Python OCR pipelines, dashboards, and cloud LLMs to turn messy unstructured data into scalable workflows, with reported impact including 70% faster document processing and 80-85% reduction in manual resume screening.”

Rasheed Samady

Screened

Entry-level AI Engineer specializing in automation and ML platforms

San Francisco, CA0y exp

“Built a production Python lead intelligence pipeline that combined external APIs, website crawling, and automated opportunity brief generation, with strong emphasis on reliability, observability, and recovery. Also has hands-on Playwright experience hardening flaky, dynamic web automations and reducing intermittent failures to under 5% through logging, screenshots, session management, and retry strategies.”

Rahul Jaiswal

Screened

Mid-level Full-Stack Developer specializing in AI-powered SaaS and web platforms

Dimapur, India3y exp

“Full-stack engineer focused on AI-powered products who has independently built end-to-end systems ranging from a food delivery platform with admin/rider workflows and payments to RAG-based LLM apps like a PDF-to-chat book assistant. Particularly interesting for teams building production AI because they speak concretely about retrieval architecture, evals, observability, fallback design, and human-in-the-loop decisions in customer support use cases.”

“AI engineer with hands-on experience shipping production systems across semantic search, RAG/LLM applications, and computer vision. Built a personalized e-commerce search platform with measurable relevance and latency gains, and deployed grounded GenAI chat systems that significantly reduced hallucinations while lowering support burden. Also brings edge-deployment experience in monocular depth estimation and 3D reconstruction, suggesting strong breadth across modern applied AI.”