Vetted Multi-Agent Systems Professionals

“Robotics software engineer with a Master’s thesis building an end-to-end monocular-vision pick-and-place controller for construction use cases on TurtleBot3 + OpenManipulator, spanning synthetic data creation, transfer learning, simulation in Gazebo, and real-robot deployment. Leveraged ROS distributed architecture to run two heavy AI models across networked GPUs to achieve usable real-time performance, and has production CI/CD experience as a Senior Software Engineer in AI/analytics.”

“AI Automation Engineer at BalancedTrust who single-handedly shipped production LLM features for FinTech compliance: a policy gap-analysis pipeline (SOC 2/GDPR) and a RAG-based regulatory chatbot. Deeply focused on reliability in high-stakes legal/compliance settings, with strong production engineering (edge functions, parallelized batching to cut latency, structured JSON outputs, guardrails, and monitoring) and close collaboration with non-technical compliance experts.”

“AI engineer at Cleveland Clinic building production LLM/NLP systems for radiology documentation, focused on HIPAA-aware, real-time performance across ~298 campuses. Re-architected infrastructure with AWS event-driven services to handle scaling and improved SLA compliance ~40%, and complements this with a personal multi-agent debate system (CrewAI) using local Llama/Mistral plus rigorous evaluation (A/B tests, red teaming, observability).”

“Built Hexagon’s production Text-to-CAD Copilot that converts text and rough sketches into editable CAD code, combining GraphRAG (Neo4j/LangChain) with a Gemini-powered vision module and multi-agent geometric validation—cutting manual modeling from a day to ~45 seconds and driving retrieval latency below 50ms. Also has large-scale GCP data/ML orchestration experience (Airflow/Cloud Composer, Dataflow, Pub/Sub, Snowflake) processing 50M+ daily records with drift monitoring and automated reliability controls.”

Shrinivas Bhusannavar

Screened

Mid-level AI Engineer specializing in agentic LLM systems and RAG platforms

San Jose, CA5y exp

“Built and shipped Serrano AI, a multi-tenant SaaS conversational AI platform that automates Odoo ERP workflows and lets ops/finance/supply-chain teams query ERP data in natural language. Implemented a multi-agent architecture (LangChain/LangGraph/CrewAI) with hybrid RAG over ERP schemas, deployed on Heroku/Vercel with production observability, cutting reporting time by ~80% while addressing hallucinations, latency, and schema complexity.”

“AI/LLM engineer who has shipped production RAG copilots and multi-agent workflows, including a real-time Llama3 (Ollama) copilot backend handling 12k+ concurrent queries at 99.9% uptime. Deep on orchestration (Langflow/Airflow/Kubernetes), reliability evaluation (hallucination detection, p95 latency, token cost), and monitoring (Prometheus/Grafana), with demonstrated stakeholder-facing analytics delivery via Tableau.”

“Entry-level candidate who built NYC Lens, a real-time Gemini-based multi-agent system that processes live camera input, identifies landmarks, and returns structured contextual insights. Despite being a fresher, they show hands-on experience with deployment on Cloud Run, modular orchestration, noisy-data handling, and reliability patterns like retries, fallbacks, and explicit state management.”

“Enterprise implementation/deployment specialist focused on HRMS and payroll systems across APAC customers, combining cloud/hybrid (AWS/Azure/GCP) integration work with strong client-facing delivery. Demonstrated ability to debug complex production issues across application, database, and network layers (e.g., isolating VPN/router congestion) and to tailor Python-based data cleaning/scoring/utilities to customer-specific workflows.”

Tyler Brown

Screened

Mid-level Forward-Deployed AI Engineer specializing in LLM automation for financial services

Atlanta, GA5y exp

“Solo builder who created a real-time AI call coaching product for sales reps in just 18 days, spanning 29 stateless edge functions, 157 SQL migrations, and ~72k lines of TypeScript. They combine strong full-stack engineering with sharp product instincts, using direct user feedback and SQL-driven observability to iterate quickly and win early paying customers without marketing.”

Raj Shrinivasan

Screened

Principal AI Engineer specializing in agentic systems and cloud-native platforms

Cleveland, OH23y exp

“Built a production RAG-powered analytics copilot at Aya Healthcare for operations leaders and analysts on a large healthcare staffing platform processing over a billion telemetry records annually. Stands out for strong production-minded agent engineering: deterministic orchestration, grounding-first design, deep observability, and data-driven workflow changes such as confidence-based human review for a PR review agent.”