Vetted GPT Professionals

“Built and deployed a production LLM-powered text-to-SQL/document intelligence chatbot on AWS that lets non-technical business users query complex enterprise databases in plain English. Demonstrates deep practical expertise in schema-aware prompting, embeddings-based schema retrieval, SQL safety/validation guardrails, and rigorous offline/online evaluation with human-in-the-loop approvals for risky queries.”

Muhammad Mohsin Khan

Screened ReferencesModerate rec.

Senior Unity XR Developer specializing in networked VR/MR collaboration

Remote, Germany10y exp

“Unity/VR developer who has shipped a Meta Quest enterprise multiplayer immersive meeting platform (Arthur Spaces) and also delivered a puzzle/quest-style Unity game release in just one month. Leverages AI-assisted Blender workflows to rapidly prototype 3D assets and accelerate MVP development, and is comfortable in both structured studio pipelines and startup-style cross-functional teams.”

“Built and deployed a production-grade, multi-agent Text-to-SQL assistant that lets non-technical stakeholders query large enterprise databases in natural language. Uses Pinecone-based schema retrieval + LLM reasoning (Gemini/Claude/GPT) with a dedicated validation agent (schema/syntax checks and safe dry runs) to reduce hallucinations and improve reliability, while optimizing latency and cost via async execution and embedding caching.”

“LLM engineer/data analyst who built a production RAG QA assistant over the Jurafsky & Martin NLP textbook to reduce hallucinations and provide explainable, source-grounded answers. Experienced with LangChain/LangGraph orchestration, retrieval optimization (embeddings, vector DBs, caching), and rigorous evaluation/monitoring (Retrieval@K, A/B tests, telemetry/drift). Previously communicated analytics insights to non-technical stakeholders at GS Analytics using Power BI and simplified reporting.”

“Built and deployed a production RAG-based multilingual analytics assistant for healthcare operations, enabling non-technical teams to query claims/EHR and risk metrics with grounded explanations. Demonstrates strong end-to-end LLM system engineering (retrieval tuning, re-ranking, hallucination controls, verification layers) plus workflow orchestration (Airflow/Composer/Step Functions) and stakeholder-driven iteration via prototypes and dashboards.”

“Built and deployed a production generative-AI copilot at Tungsten that automates invoice/form extraction template creation, reducing weeks of manual model-building work. Combines fine-tuned LLMs (PyTorch/HuggingFace) with OpenCV layout grounding to reduce hallucinations, and runs an end-to-end Kubeflow-based MLOps pipeline with drift monitoring, canary releases, and automated retraining.”

Avanishika Revelli

Screened

Junior Software Engineer specializing in backend, cloud, and robotics automation

2y exp

“Graduate Research Assistant in Robotics at Arizona State University who built an end-to-end LLM-driven task execution framework enabling collaborative robots to convert high-level natural language instructions into safe, executable ROS actions. Implemented robust monitoring, failure detection, and automatic replanning, and addressed real-world issues like timestamp/frame-transform mismatches and heterogeneous robot interoperability using adapter nodes.”

“Built and deployed a "personal second brain" product (CloneMind) with an end-to-end RAG pipeline for retrieving information across PDFs, URLs, images, and audio using Next.js/Node.js/Postgres/Supabase/Redis. Demonstrates strong practical depth in retrieval quality tuning, latency reduction via caching, and stateful orchestration with LangChain/LangGraph, plus experience persuading a non-technical professor stakeholder by shipping a working prototype.”

“Built and shipped a production LLM-powered incident response agent for a microservices platform, automating alert triage and safe remediation recommendations with strong guardrails (RAG grounding, structured JSON outputs, rule-based validation, and human-in-the-loop). Implemented state-machine orchestration (Redis/Kafka), comprehensive eval/monitoring, and an error categorization pipeline that cut hallucination errors ~40% and reduced MTTR ~30%.”

“Built an end-to-end agentic population health strategy copilot for healthcare leadership, turning broad chronic disease questions into structured, evidence-backed strategy briefs. Stands out for combining healthcare domain knowledge with production-grade GenAI implementation, including LangGraph orchestration, Databricks/MLflow deployment, human review, and quality gates focused on citations, metrics, risks, and safety.”

“AI/ML engineer with 9+ years of experience building production recommendation and LLM systems end-to-end, from experimentation through deployment, monitoring, and retraining. Stands out for combining strong MLOps discipline with practical GenAI/RAG implementation, including measurable impact such as ~25% higher engagement on an e-commerce recommender and nearly 30% faster knowledge retrieval from internal documents.”

“ML/AI engineer with hands-on experience building healthcare and fraud-detection systems from experimentation through deployment, monitoring, and retraining. Stands out for combining real-time IoT pipelines, cloud-native MLOps, and GenAI/RAG in regulated healthcare settings, with reported impact including reduced emergency response times and a 25% reduction in manual diagnosis time.”