Vetted Multi-Agent Systems Professionals

“Built and deployed a secure, production LLM-based document summarization and risk-highlighting tool for financial auditors, running inside a private Azure environment to protect confidential data. Focused on reliability (hallucination mitigation via retrieval-based prompts and source citations) and validated performance through comparisons to auditor summaries plus a user pilot, cutting review time by about half.”

Rowan Ramamurthy

Screened

Mid-level Robotics Software Engineer specializing in multi-robot control and automation

Atlanta, GA4y exp

“Robotics software engineer with ~7 years of ROS/ROS2 experience spanning dual-arm metal additive manufacturing and prior work on the DARPA Subterranean Challenge. Developed in-house multi-arm collision/trajectory planning and achieved a major calibration improvement (from ~6 cm error to ~0.5 mm) via ICP point-cloud registration, with strong simulation/digital-twin, SLAM, and deployment (Docker/CI/CD) exposure.”

xiaowei guo

Screened

Junior Game Designer specializing in AI-driven systems and interactive narrative

Irvine, CA2y exp

“Game economy/progression designer who owned an end-to-end multi-currency economy for a top-down kitchen management sim, balancing cash/reputation/XP with sinks like spoilage, maintenance, and rent. Uses telemetry + structured playtests and spreadsheet simulations to tune pacing, reduce mid-game churn, and prevent late-game inflation by adjusting efficiency/skill curves and phase-based balancing.”

Manoj Manjunatha

Screened

Junior Software Engineer specializing in full-stack and AI-powered web systems

Boise, ID3y exp

“Built the backend for “codeGuard,” an AI-powered static code analysis platform, using FastAPI and Docker. Structured the system into API/service/execution layers and addressed heavy-workload container resource/cleanup issues via strict CPU/memory limits and a queued execution model.”

“AI/ML-focused engineer with practical experience building RAG-based and multi-agent systems, including architectures for retrieval, reasoning, context processing, and response generation. Stands out for combining LLM productivity gains with disciplined software engineering practices like validation, monitoring, and reproducibility.”

“Robotics engineer with a 2024 internship building an end-to-end software stack for an autonomous humanoid robot that follows natural-language audio commands to make coffee and deliver snacks, including perception (OpenCV), mapping, and ROS Navigation. Also contributing to a robotics foundation model effort by building data preprocessing pipelines using GroundingDINO and SAM2, and has multi-robot coordination experience with algorithms designed to handle real-world communication drops.”

“Software engineer working on an e-commerce platform, currently building a RAG-based recommendation system with a team new to the technology. Has delivered an end-to-end React/TypeScript website for a local car dealer and built an internal "encryption as a service" tool to secure sensitive data across repositories and through release/UAT, with experience debugging microservices integration issues.”

“Research-focused AI engineer who built an agentic pipeline to automatically extract Sphinx-based API documentation/changelogs and generate synthetic tasks for a dynamic LLM code benchmark targeting real-world API evolution and deprecations. Experienced with multi-agent orchestration (AutoGen, LangChain, CrewAI) and rigorous evaluation methods, and has prior multi-agent work from a Microsoft Research internship.”

“Red Hat ML/LLM engineer who designed and deployed a production LLM-powered customer support automation system using RAG, improving latency by 30% via PEFT and vector search optimization. Built security and governance into retrieval (access-level filtering, encrypted Pinecone/ChromaDB) and delivered SHAP-based explainability via a dashboard for non-technical stakeholders. Experienced orchestrating distributed ML/RAG pipelines across AWS SageMaker and OpenShift with Airflow/Prefect, plus multi-agent workflows using CrewAI and LangGraph.”

Yan-Liang Chen

Screened

Junior Robotics Systems Engineer specializing in autonomous planning and control

Champaign, Illinois2y exp

“Robotics software engineer focused on autonomous surface vehicles, specializing in dynamic collision avoidance and regulation-compliant navigation. Extended ROS2 Nav2 by implementing a Velocity-Obstacle-based safety filter (as a DWA critic) and encoding COLREGs, plus built an end-to-end Gazebo+ArduPilot SITL stack and a ROS2 bridge translating Nav2 commands to ArduPilot for real-world deployment.”

Saisureshreddy Challa

Screened

Mid-level Data Scientist specializing in AI/ML, LLMs, and domain analytics

California, USA6y exp

“BlackRock AI/ML engineer who built and owned a production LLM document intelligence system for regulatory and investment analysis end-to-end. They combined RAG, multi-agent validation, strong evaluation/monitoring, and reusable Python services to process 50K+ documents, cut review time 40-50%, and improve decision accuracy by about 25%.”

Thomas Le

Screened

Junior Full-Stack Software Developer specializing in web, mobile, and health tech

Remote2y exp

“Developer who uses AI as a productivity accelerator while maintaining strong ownership of code quality, security, and readability. Built an AI-powered planning tool during the PolyPrompt hackathon that transformed messy project requirements into structured tasks, timelines, and assignments, and has also led human teams through Veggie Rescue with a focus on user-aligned execution.”

“UCLA RoMeLa research assistant (since Oct 2025) building an embedded control and sensor-data platform for multi-robot coordination in a simulated warehouse. Deep hands-on experience with ROS on NVIDIA Jetson under RTOS constraints, secure MQTT/TLS telemetry, and SLAM performance optimization (including ORB-SLAM3) validated in Gazebo and deployed via Docker/Kubernetes and CI/CD.”

“Built an LLM multi-agent “ingredient safety” analyzer for cosmetics that cuts consumer research time from ~20+ minutes to minutes, using LangGraph orchestration, hybrid retrieval (Qdrant + Tavily), and safety-focused critic validation (false rejections reduced ~30%→~8%). Also has research-internship experience building computer-vision pipelines to classify emerald color/clarity by translating gem-expert heuristics into quantitative model features.”

“Siemens AI engineer who shipped production multi-agent LLM systems across cybersecurity and sustainability, including a vulnerability automation agent that cut manual work 70%. Deep in orchestration (LangGraph supervisor-worker state machines), reliability engineering (async fault tolerance, retries, spike handling), and rigorous evaluation (offline benchmarks, LLM-as-a-Judge improving label agreement 28.9%) with measurable production guardrails.”

Shao Rong Su

Screened

Senior AI Research Engineer specializing in LLM agents and predictive maintenance

5y exp

“At Delta Electronics, partnered with automotive firmware teams to productionize an LLM-based coding assistant for identifying safety standard violations and generating bug-fix guidance. Built an agentic workflow with stepwise context extraction, similarity search, and a separate judge model for scoring reasoning/retrieval, and drove internal adoption through pain-point discovery and tailored technical demos using real firmware code.”

Junhui Huang

Screened

Intern Machine Learning Engineer specializing in LLMs, MLOps, and NLP

Providence, RI1y exp

“Built and deployed a production LLM-driven Dungeons & Dragons game where the model acts as a dungeon master, adding a structured combat system and a macro-state tree to ensure campaigns converge to a clear ending. Fine-tuned Gemini 2.5 Flash on Vertex AI and deployed on GCP with Kubernetes, using RAG over DnD rules/spells plus multi-agent orchestration (intent-based routing between narrative and combat agents) to reduce hallucinations and improve reliability.”

“Early-career analytics candidate with hands-on experience in SQL/Python data pipelines, Tableau reporting, and marketing engagement analytics across internship and startup settings. Stands out for combining rigorous data quality practices with practical AI system design, including an end-to-end GPT-4 grading capstone that emphasized explainability and human oversight.”

“Built and owned Alight's AI-powered Search Summary feature end-to-end, using a RAG pipeline with OpenSearch and Bedrock, and drove a 20% increase in user feedback scores. Stands out for bringing rigorous production evaluation to LLM systems via live LLM-as-a-judge monitoring, and for experience with advanced agentic architectures, hybrid search, and reranking at scale.”

“AI/backend engineer who has owned production applied-ML systems end to end, including a Jitsi meeting intelligence platform with custom RoBERTa boundary detection, LLM summarization, and automated retraining from user feedback. Also has healthcare AI experience building a diabetes medication titration system with strict validation, drift monitoring, and safety guardrails—showing both product speed and high-stakes engineering rigor.”

“Built a production AI-driven QA automation platform using a multi-agent architecture (MCPs + LangGraph) to run parallel website tests across multiple device environments via automated image building and containerization. Currently collaborating with restaurant operators and managers to deliver an agentic restaurant analytics system, emphasizing deep domain discovery with non-technical stakeholders.”

Yasser Ali

Screened

Junior AI & ML Engineer specializing in agentic systems and full-stack AI products

San Francisco, CA2y exp

“Won a machine learning contest and was placed onto a Kaiser data science team, where they built ML models for hospital bottleneck prediction and resource allocation. They later built and deployed a full-stack LLM-based “data analyst agent” (with custom orchestration plus LangChain/OpenAI Agents experience) that generates analysis code, answers questions, and produces dashboards from uploaded datasets, emphasizing rigorous evaluation sets, robustness, and healthcare security/compliance integration.”

“Backend/ML engineer who built and operated a production WhatsApp assistant end-to-end using a modern RAG stack, delivering >90% automation with sub-2-second latency. Shows strong depth in retrieval quality, observability, evaluation, and incident handling, and has also applied similar AI workflow patterns to a clinical diagnostic assistant processing medical PDFs.”

“Revamped a university academic calendar system into a Python-based calendar generation service, turning a weeks-long manual scheduling workflow into software that generates dozens of valid calendar combinations in under a minute. Also contributed to an Amazon search ML classifier by introducing precision/recall evaluation to better surface critical failure modes and improve prediction quality.”