Vetted Multi-Agent Systems Professionals

“Candidate brings an operator-to-founder profile with leadership experience in IT and Business Systems and a strong grasp of how ideas become venture-backable products. They speak fluently about startup evaluation criteria such as TAM, technical defensibility, speed to scale, and AI differentiation, and appear especially motivated by building solutions end-to-end in startup or venture studio environments.”

“SDE who worked on an MGICS Lab robotics project building a multi-agent model to help agents understand tasks and generate robot instructions, emphasizing task-splitting, checking, and a reflection agent to improve accuracy. Also has experience using GitHub with automated CI/CD pipelines.”

“Cloud-focused engineer experienced deploying and stabilizing complex production systems that span APIs, infrastructure, and automated workflows, with a strong observability and safe-release mindset (feature flags/canaries/rollbacks). Has hands-on, customer-facing incident leadership, including executing DR regional failover during an AWS us-east-1 outage to maintain service and reportedly save a client ~$10M.”

“Built and productionized a telecom-focused RAG assistant by LoRA fine-tuning LLaMA-2 and integrating LangChain+FAISS behind a FastAPI service, with dashboards and a human feedback UI for engineers. Demonstrated measurable impact (≈40% faster document lookup, +8–10% retrieval precision) and strong MLOps rigor via Airflow orchestration, CI/CD, and monitoring for drift and failures.”

“Insurance-tech CTO and repeat founder with 10+ years in insurance startups; was employee #4/CTO at Polly (formerly DealerPolicy) and helped scale it from a PowerPoint to 250 employees while raising $180M+. Currently building and selling AgentCanvas.ai—an extensible AI accelerator platform for large insurance agencies—after coding the product end-to-end and now running demos/POCs with prospective buyers.”

“LLM engineer who built a production seller-support RAG system at eBay using hybrid retrieval (BM25 + Pinecone vectors) with Cohere reranking, LangGraph orchestration, and citation-grounded answers. Strong focus on reliability: semantic/structure-aware chunking, automated Ragas-based evaluation with nightly regressions, and production observability (LangSmith) plus drift monitoring (Arize). Also implemented a multi-agent fraud pipeline with AutoGen using JSON-schema contracts and explicit termination conditions.”

Aashna Kunkolienker

Screened

Junior AI Engineer specializing in agentic workflows and ML platforms

San Ramon, CA2y exp

“Building a production LLM/agent system for a leading US dental provider that extracts rules from payer handbooks/portals and EDI 271 responses to validate and improve patient cost estimates. Combines GCP stack (BigQuery, GKE, Cloud Run, Pub/Sub, Vertex AI) with strong agent reliability practices (observability, validator agents, grounding, PII/hallucination guardrails, confidence scoring) and has led non-technical customer stakeholders on enterprise ServiceNow↔Aha sync and AI-powered enterprise search/summarization.”

Jainum Sanghavi

Screened

Mid-level DevOps Engineer specializing in cloud automation and Kubernetes platforms

Boston, MA2y exp

“Robotics/ML engineer who has built SO(3)-equivariant models for robotic manipulation, including custom equivariant layers and differentiable point-cloud rasterization/derasterization workflows. Also brings 2 years of DevOps experience in banking systems, automating CI/CD and infrastructure at scale (managed 180 OCI servers; reduced rebuild downtime by 80%).”

silin liu

Screened

Mid-level AI/ML Engineer specializing in LLM agents, RAG, and enterprise ML systems

New York City, NY5y exp

“Built a production multi-agent recommendation/RAG system for internal data analysts to speed up weekly report creation by improving document discovery and automating report/SQL generation. Implemented LangGraph-based orchestration with deterministic agent routing, robust error handling (interrupt/resume), and metadata-driven semantic chunking for diverse PDF/document formats, plus monitoring for latency, throughput, and token/cost efficiency.”

Ibrahim Kurban Ozaslan

Screened

Junior Robotics & Controls Researcher specializing in optimization, MPC, and reinforcement learning

Los Angeles, CA

“Robotics software candidate who designed and implemented a hierarchical motion-planning and whole-body control pipeline for a 37-state Spot robot to traverse complex terrain, using Graph of Convex Sets for safe footstep selection plus optimization-based IK and nonlinear trajectory optimization for joint trajectories/contact forces. Strong in optimization-heavy robotics workflows (PyDrake, MATLAB/Simulink) and methodical debugging down to signal-level and numerical stability; has not used ROS/ROS2 yet.”

Shivam Udeshi

Screened

Intern Robotics/ADAS Engineer specializing in perception, sensor fusion, and state estimation

2y exp

“Robotics software engineer who built a multi-agent dense warehouse mapping system in ROS 2, including LiDAR-camera fusion SLAM, timestamp-based synchronization, and DDS-based inter-robot pose/keyframe exchange under bandwidth constraints. Also applied Gaussian Splatting for selective photorealistic dense reconstruction and optimized real-time performance with node composition, bounded queues, and QoS tuning; experienced with Gazebo/CARLA/Unity simulation and Dockerized ROS 2 deployments.”

Shravya Shashidhar

Screened

Intern Software Engineer specializing in LLM agents and full-stack development

Seattle, USA1y exp

“Embedded C++ engineer with Bosch automotive infotainment experience, owning real-time audio middleware modules with strict latency/memory constraints. Strong in profiling/optimizing deterministic behavior, debugging hardware-specific intermittent issues, and building automated test + CI pipelines; currently ramping up on ROS2 concepts (DDS, nodes/topics/services) to transition toward robotics.”

Devang Shah

Screened

Executive AI and Cloud transformation leader specializing in enterprise GTM and product engineering

San Jose, CA23y exp

“Candidate is interested in building horizontal AI infrastructure capabilities, specifically around observability, and brings exposure to investor evaluation dynamics from experience at PE-backed firm WinWire. They appear strongly motivated by entrepreneurial ownership, creativity, and the ability to drive and pivot ideas in a venture studio or startup environment.”

“VR/social platform engineer with experience at AltspaceVR, Mozilla Hubs, and Dopple, spanning Unity/C#, custom engine networking, and early voice-agent systems. Particularly compelling for roles at the intersection of multiplayer, XR, and AI: they’ve built data-driven avatar systems, ownership-based netcode, VR replay capture, and a custom real-time voice->LLM->voice stack integrated with hardware and computer vision.”

“Senior software engineer with hands-on experience leading multi-agent AI workflows in financial trading infrastructure. Most notably, they applied a specialized agent setup on a high-frequency trading backend to cut delivery time from three weeks to ten days while improving validation against risk, performance, and compliance requirements.”

“At Evoke Tech, built a production LLM "Testbench" to quickly compare LLMs/embedding models and RAG strategies (semantic, hybrid BM25, re-ranking, HyDE, query expansion) to select optimal architectures for different client needs. Also developed a multi-agent, multimodal (voice/text) RAG system for live catalog retrieval and safe product recommendations using LangGraph/LangChain with LangSmith monitoring, and regularly translated PM/UX goals into concrete agent behaviors via demos and flowcharts.”

“Amazon engineer who built a production AI agent platform (Python/AWS Strands on Bedrock) that lets teams create tool-using, multi-agent workflows—e.g., agents that auto-triage and resolve customer support tickets by reading internal documentation and collaborating with a research agent. Previously worked in Deloitte on IAM using Ping Identity/Ping DaVinci orchestration, and applies orchestration thinking plus structured evaluation (LLM-as-judge, surveys, automated tests) to improve agent reliability.”

“Built ToolDreamer, a framework for selecting relevant tools for LLM agents by training a retriever on LLM-generated reasoning traces, and has hands-on experience building multi-agent systems in AutoGen (MAG-V) focused on question generation and tool-trajectory verification. Currently works as an AI-guides supervisor at Penn State, regularly communicating AI concepts to non-technical stakeholders.”