Vetted Retrieval-Augmented Generation 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).”

“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.”

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 deployed a production bilingual (Bengali/English) AI virtual assistant that replaced IVR for telecom customer service at massive scale (~15M users), integrating ASR/TTS, Rasa dialogue management, and custom NLP. Overcame low-resource Bengali data and noisy call-center audio with synthetic data augmentation and transformer fine-tuning, achieving significant production gains including ~50% reduction in support calls.”

“Recent graduate who independently built scholar.ai from scratch in roughly two weeks, shipping a full multimodal ingestion, retrieval, and grounded Q&A system for students. Also created Anchor SDK, an open-source framework for runtime hallucination detection and recovery, showing unusually strong depth in production LLM systems, evals, and reliability for an early-career candidate.”

“Built and deployed an LLM-powered automation pipeline that ingests voice and documents, transcribes/extracts key information into structured data, and routes it through backend workflows using Python/FastAPI. Uses n8n to orchestrate multi-step AI processes with validation, retries, and monitoring, and iterates with stakeholders via rapid demos to refine changing requirements.”

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).”

Sarang Pratham

Screened

Junior Software Engineer specializing in data engineering and GenAI

Kundapur, India3y exp

“Built and deployed a production LLM-powered recruitment chatbot that automates key recruiting steps (sourcing, candidate engagement, screening). Strong in agent orchestration with LangGraph, including guided graph-based workflows, context-aware routing, and reliability measures like clarifying steps plus human-in-the-loop evaluation.”

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.”

“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.”

“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.”