Vetted AI & Machine Learning Professionals

“Built and shipped a production LLM-powered multi-agent RAG system to automate complex internal support workflows, integrating tool execution (SQL/APIs) with validation guardrails to reduce hallucinations. Optimized for real-world latency and cost via model routing, caching, and async parallel tool calls, and enforced reliability with CI-gated golden test sets derived from anonymized production queries.”

“Lab automation engineer building an automated weighing robot system for Lilly’s analytical chemistry group, integrating a 6-axis Mecademic robot, Mettler Toledo balance, and vision/barcode verification with safety protocols for live lab operation. Experienced in production Python for instrument control, data processing, and CV/ML, including authenticated Data Lake API integrations with fault handling. Also improved automated sample storage throughput 2–3x via pick-order optimization and partners closely with scientists to deliver MVP-to-production experimental automation workflows.”

“Built a production LLM-powered RAG agent for healthcare/insurance operations that retrieves and summarizes patient medical documents with grounded citations, scaling to ~4.5M records. Addressed medical shorthand and terminology by fine-tuning ~120 lightweight DistilBERT models by specialty and validating entities against SNOMED/RxNorm, while using SHAP/LIME and human-in-the-loop review to make decisions explainable to stakeholders.”

“AI engineer with production experience building a high-accuracy (98%) fraud detection system operating at real-time latency (1–2s) over millions of transactions, using a multi-model pipeline approach to meet performance constraints. Also implemented Airflow-orchestrated workflows (DAGs, retries, alerts) to replace brittle cron scripts and is currently pursuing a master’s project on real-time ASL-to-text conversion.”

“ML/LLM engineer who built production systems to speed up artist content-creation workflows, including a fine-tuned image captioning model paired with a RAG layer over image embeddings/captions to improve consistency across changing domains. Experienced orchestrating multi-tool agents with LangChain/LangGraph (planning + critic/reflection) and setting up practical monitoring (caption rejection rate) plus evaluation sets for tool-calling accuracy, output quality, and latency.”

“LLM/agentic systems builder at Verizon who deployed a LangGraph-orchestrated multi-agent ticket-automation platform with RAG (FAISS) to replace brittle rule-based bots. Improved routing correctness by ~30–40%, hit ~300ms latency targets via model routing, and reduced ops workload by ~60% through tight iteration with non-technical stakeholders and strong testing/observability practices.”

“Full-stack engineer at Bank of America who built and iterated a real-time transaction monitoring/fraud detection system processing 50K+ daily transactions, improving latency (25%), dashboard performance (30%), and reducing manual investigation time (40%) while meeting PCI DSS via OAuth2 and RBAC. Also built a scalable ETL pipeline for messy financial data with strong reliability/observability (ELK, retries, DLQ), boosting data integrity from 87% to 99% and sustaining 99.8% uptime.”

“Gameplay/AI engineer with end-to-end ownership of racing-sim AI (fair physics parity, competitive overtaking) and strong iteration tooling (live tuning + config). Has shipped networked VR multiplayer work at Ready At Dawn, including a consensus-style goal validation approach to reconcile non-deterministic replication/smoothing discrepancies, plus experience with Havok/Bullet, spline math (Catmull-Rom), and complex creature/boss animation behaviors.”

“AI Engineer (Medtronic) who deployed a production RAG-based clinical assistant grounded in curated biomedical literature (no patient-identifiable data). Deep hands-on experience orchestrating and hardening LLM workflows with LangChain/LangGraph, including stateful agentic flows, rigorous testing, and evaluation; reports a 72% accuracy improvement through retrieval enhancements (query rewriting, multi-query expansion, MMR reranking).”

“Built and deployed a production LLM/RAG fraud investigation system to replace manual investigator workflows, combining transaction data, historical cases, and policy documents with agent-style steps and LoRA fine-tuning. Demonstrates strong reliability engineering (grounding, citations, abstention paths), performance optimization (retrieval/indexing/caching), and end-to-end MLOps orchestration using Azure ML Pipelines/MLflow plus Kubernetes/Argo with canary and rollback deployments.”

“Built a production agentic AI system to automate data science work using a layered architecture (executive-summary handling, tool-based execution, and on-the-fly code generation). Demonstrates strong end-to-end agent development practices including RAG with vector databases, prompt engineering, and multi-method evaluation (LLM-as-judge/human/code-based), plus Airflow-based orchestration for ML data pipelines and close collaboration with business end users.”

“Built and shipped a production LLM-powered RAG assistant for enterprise internal document search (PDFs, knowledge bases, structured data), addressing real-world issues like noisy documents, hallucinations, and latency with grounded prompting, retrieval-confidence fallbacks, and performance optimizations. Also partnered with compliance and business teams at JPMc to deliver a solution aligned with regulatory constraints, supported by monitoring, feedback loops, and systematic evaluation.”

“Summer SDE intern at AWS who built and deployed a column-lineage debugging tool for on-call engineers, using AWS Bedrock to parse SQL and generate a column DAG. Integrated the tool into an existing validation system and hardened it against real-world SQL format differences via flexible parsing and testing with queries from multiple upstream teams.”

“AI/ML engineer (Cognizant) who built a production, real-time credit card fraud detection platform combining deep-learning anomaly detection with an LLM-based explanation layer. Strong focus on regulated deployment: addressed class imbalance and feature drift, and added guardrails (SHAP/structured inputs, fine-tuning on analyst reports, rule-based validation) to keep explanations accurate and compliant. Orchestrated the full pipeline with Airflow + Databricks/Spark and used MLflow/Prometheus plus A/B and shadow deployments for measurable reliability.”