Vetted Model Evaluation Professionals

“New grad SDE (AI/ML) who built and deployed an LLM-based chatbot framework used across technology, military, and banking contexts, focusing on model selection tradeoffs (latency vs accuracy) through prototyping and benchmarking. Also built a multi-agent "eaterybot" using PyAutoGen/AutoGen with a manager agent orchestrating specialized agents, and emphasizes rigorous testing with adversarial/edge-case datasets and hallucination checks.”

“Built production LLM systems including a real-time customer feedback analysis and workflow automation platform using RAG and multi-agent orchestration with confidence-based human escalation, addressing privacy and legacy integration challenges. Also automated ML operations with Airflow/Kubernetes (e.g., daily churn model retraining) cutting retraining time to under 30 minutes, and demonstrates a rigorous testing/monitoring approach plus strong non-technical stakeholder collaboration.”

“Backend/ML-leaning engineer who built a content-based event recommender for FlowMingle using embeddings + HNSW vector search on Google Cloud, with Firebase as the backend and a managed recommendation lifecycle (15 recs/user, daily async generation, weekly deletion) now serving 1500+ users. Also led a cost-driven migration of ConvAI services to Azure AI using parallel request testing from a Unity client, with post-migration monitoring via logs and model evals; contributed to a Massachusetts law-enforcement conversation analysis system by expanding ingestion to PDF/TXT/Excel and multi-file inputs.”

“LLM/agent engineer who built a production LangGraph multi-agent orchestrator connecting GitHub and APM/observability signals with a chain-of-verification loop for root-cause analysis. Emphasizes pragmatic architecture (start simple with state summaries), performance tuning (async LLM calls, Docker), and rigorous evaluation (LLM-as-judge, adversarial testing, hallucination/instruction adherence metrics, tool-call tracing) while iterating with non-technical stakeholders via A/B testing.”

“Built and deployed a production LLM-powered calorie-counting chatbot that turns plain-English meal descriptions into normalized food entities, quantities, and calorie estimates using a hybrid transformer + rule-engine pipeline. Emphasizes reliability with schema/constraint guardrails, confidence-based routing (including embedding similarity search fallbacks), and strong observability/metrics (hallucination rate, calibration, latency, cost). Partnered closely with nutritionists to encode domain standards into mappings and validation logic.”

“Built and deployed a production-style vision-language pipeline that generates structured medical reports from chest X-rays using BioViLT embeddings, an image-text alignment module, and BiGPT fine-tuned with LoRA, delivered via Streamlit and hosted on AWS EC2. Also collaborating experience presenting EDA findings, feature importance, and model performance to Ford managers while working with vehicle parts data at Bimcon.”

“React performance-focused engineer who contributed performance patches back to an open-source context+reducer state helper after profiling and fixing excessive re-renders in an enterprise project management platform at Easley Dunn Productions. Also built an end-to-end LLM-driven pipeline at Prime Healthcare to normalize millions of supply-chain records, reducing defects by 80% and saving 160+ hours/month.”

“ML practitioner with hands-on experience in healthcare time-series modeling (CGM-based blood glucose prediction) including a novel ICA-based blind source separation approach and robust data-cleaning for noisy, missing sensor data. Also built an embeddings + LLM-powered podcast recommendation workflow using YouTube transcript scraping and Vellum AI document indexing, with a strong emphasis on production-grade engineering practices (TDD, monitoring) and realistic rolling validation for forecasting.”

“AI/ML engineer who built a production RAG-based internal document intelligence assistant (LangChain + Pinecone) to let employees query enterprise reports in natural language. Demonstrated hands-on pipeline orchestration with Apache Airflow and tackled real production issues like retrieval grounding and latency using tuning, caching, and token optimization, while partnering closely with non-technical business stakeholders through iterative demos.”

“Built and owned an end-to-end RAG-based AI support platform at Mechanize (FastAPI/LangChain/Pinecone/React) with rigorous evals and guardrails, driving 45% fewer support tickets and ~$280K annual savings. Also led a high-risk legacy modernization at Argo AI, incrementally extracting a monolithic Django backend using Strangler Fig + feature flags while supporting 10K+ concurrent users.”