Vetted Multi-Agent Systems Professionals

“LLM/agentic systems practitioner who specializes in moving demo-only assistants into reliable, observable, cost-controlled production services. Strong in real-time diagnosis of complex agent workflows (including tracing, loop detection, and guardrails) and in customer-facing enablement—running workshops, building tailored PoCs, and partnering with sales to close deals by proving reliability in high-risk pilots.”

“Built and scaled a multi-agent LLM automation pipeline during a fintech internship, growing from a rapid 1-week proof-of-concept to a 15+ agent hierarchical system that cut market brief report generation time from ~5 hours to under 30 minutes. Hands-on with agent frameworks (Haystack, CrewAI, LangChain) and experienced in debugging agent communication issues via sandboxed modular testing and context/token management; also regularly gives architecture-first technical demos at multiple hackathons and university events.”

“Built and shipped a production LLM-powered internal operations automation platform using LangChain RAG (Pinecone) and FastAPI microservices, deployed on AWS EKS, serving 10k+ daily interactions. Implemented a rigorous evaluation/observability stack (golden datasets, prompt regression tests, MLflow, retrieval metrics, hallucination monitoring) that drove hallucinations below 2% and improved reliability, and partnered closely with non-technical ops leaders to cut manual lookup work by 60%+.”

Dan Sorensen

Screened

Executive CISO specializing in cybersecurity strategy, AI governance, and enterprise risk

Denver, CO10y exp

“Founder of Nexus Security Advisors, an early-stage cybersecurity consulting firm focused on supporting small and mid-sized businesses with practical security needs. Brings cybersecurity leadership plus AI governance and compliance focus, and has experience designing and delivering hands-on cyber threat intelligence training by validating needs with leadership and partnering to build a practical curriculum.”

“Built and productionized a multi-agent, LLM-powered document understanding system to replace manual review of long documents, using LangGraph orchestration plus RAG to reduce hallucinations. Implemented layered reliability controls (structured templates, checker agent, and human-in-the-loop feedback) and reported ~40% speed improvement after orchestration; also has hands-on Airflow experience for scheduled data pipelines.”

“LLM/agentic systems builder who has deployed multi-agent educational chatbots using LangChain + LangGraph, with LangFuse-based tracing and FastAPI hosting. Focused on production reliability and performance (latency reduction via agent decomposition and caching) and on evaluation/testing (routing test scenarios, LLM-as-judge). Partnered with product to add image understanding by parsing and storing images in S3, expanding chatbot coverage to 30+ books with images.”

“LLM/agent engineer who shipped a two-stage AI recruitment screening platform at Foursquare that automated resume ingestion through behavioral assessment, delivering an 85% reduction in screening time across 5,000+ applications with auditability and confidence-gated decisions. Also built a multi-agent benchmarking framework using MCP tool interfaces and a RAGAS + LangSmith evaluation/observability stack, including async re-architecture that cut production latency by 50%.”

Ramtin Kazemi

Screened

Junior Full-Stack Software Engineer specializing in Django, AWS, and AI/ML

San Diego, California1y exp

“Full-stack engineer who built and owned an AI-powered personal statement editor in Next.js (App Router + TypeScript), including dynamic routing, server-side data fetching, and typed API route handlers. Post-launch, they handled production monitoring/debugging and shipped reliability/performance upgrades (rate limiting, retries, rollback, DB indexing), and report a 40% latency reduction using Suspense/streaming and React concurrency patterns. Also implemented a durable Temporal-orchestrated AI document workflow with robust retry/idempotency strategies.”

Ronald Brockmann

Screened

Executive technology leader specializing in cloud, AI, video, and embedded systems

San Francisco Bay Area, CA32y exp

“Serial startup founder with multiple prior ventures that raised capital, now building an AI supervision product focused on child safety in online gaming. Has repeatedly operated in new technology categories such as WiFi, video over IP, cloud gaming, and AI supervision, and approaches validation through customer interviews, industry research, and bootstrapped market proof.”

“Built an internal RAG assistant for financial documents using FastAPI, OpenAI APIs, and vector search, improving document search speed and reducing manual effort for the business team. Stands out for a pragmatic approach to AI engineering: uses AI heavily for productivity, but keeps human judgment central and has designed retrieval, validation, and summarization workflows end-to-end.”

“Engineer working on high-throughput financial systems who uses AI pragmatically to accelerate development without sacrificing design ownership, correctness, or compliance. Particularly interesting for teams building regulated, real-time platforms: they have hands-on experience integrating fraud detection models into microservices, handling transaction ingestion, scoring, decisioning, and throughput-sensitive asynchronous workflows.”

“Built and deployed LLM-powered agentic systems including a multi-agent travel planning assistant using LangChain, RAG (FAISS), real-time APIs, and a supervisor agent to manage coordination and reduce hallucinations. Also developed a Text-to-SQL system with schema-aware validation guardrails, and collaborated with drilling domain experts at CNPC USA to build an ML model predicting rate of penetration (ROP).”

“Small-team builder of Promethium’s “Mantra” next-gen agentic text-to-SQL engine, using vector DB + LangGraph tooling and SQL validation/evaluation to improve query accuracy. Experienced in diagnosing production LLM workflow failures via LangSmith traces and in running hands-on developer workshops and pre-sales POCs with live debugging and real customer data.”

“GenAI/LLM ML engineer (currently at Webprobo) building an enterprise GenAI platform with document intelligence and automation on AWS and blockchain. Has hands-on experience with RAG, LLM evaluation tooling, and orchestrating production LLM workflows with Apache Airflow, plus deep exposure to reliability challenges in globally distributed/edge deployments. Also partnered with business/marketing stakeholders at a banking client to deliver an AI-driven customer retention insights solution.”

Rishitha reddy katamareddy

Screened

Mid-level Generative AI & Machine Learning Engineer specializing in agentic LLM systems

USA4y exp

“Built and deployed a production agentic LLM knowledge assistant that answers complex questions over internal documents, APIs, and databases using a RAG architecture (FAISS/Pinecone) and LangChain/LangGraph orchestration. Emphasizes production-grade reliability and hallucination control through grounding, confidence thresholds, validation, retries/fallbacks, and full observability (logging/metrics/traces) with continuous evaluation and feedback loops.”

Sampada shelke

Screened

Mid-level Machine Learning Engineer specializing in NLP, LLMs, and applied research

La Jolla, CA3y exp

“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.”

Sumit Kothari

Screened

Junior AI/Full-Stack Engineer specializing in LLM apps and RAG systems

Los Angeles, CA1y exp

“AI engineer who built and shipped a production AI document-understanding/search system at Sumeru Inc, including a full RAG + LLMOps evaluation stack (MLflow, DeepEval, RAGAS) deployed on GCP. Also developed LangChain/LangGraph multi-agent workflows for UAV flight-log analysis and has experience presenting AI solutions to non-technical stakeholders and prospect clients to drive POCs.”

Qichen Zhao

Screened

Intern Software Engineer specializing in Applied AI and LLM systems

Los Angeles, CA0y exp

“Built and deployed a production RAG-based conversational "Yelp for AI tools" at Search-AI Inc., focused on personalized, explainable AI tool recommendations from thousands of options. Emphasizes production-grade reliability and performance (hybrid retrieval, async two-stage pipelines) and is also building a multi-agent orchestration layer (MAgIc) with typed memory and controlled coordination policies.”

Hadi Jaffery

Screened

Junior Data Engineer specializing in Snowflake and investment data platforms

Boston, MA3y exp

“Private markets/private credit data engineer owning core Snowflake/AWS data infrastructure (S3 → ActiveBatch → Snowflake) with automated iceDQ quality checks and curated datasets for internal Power BI/React reporting. Drove major reliability and delivery improvements, including cutting DB CI/CD deploy time 50% and reducing downstream table errors by 90%+, and also built an internal React/FastAPI app to visualize the team’s data infrastructure in an ambiguous early-stage environment.”

“Built and shipped a production LLM-driven data harmonization/record-matching pipeline for pharmaceutical datasets, combining normalization, embeddings/vector search, and an LLM validation step. Emphasizes production reliability via guardrails, confidence thresholds, idempotent/retryable stages, and human-in-the-loop fallbacks, with monitoring focused on manual review and error rates to reduce false positives.”

Aravind Mohan

Screened

Junior Software Engineer specializing in AI agents and backend systems

Seattle, WA5y exp

“Backend/AI workflow engineer who built a production event-personalization service (FastAPI + AWS Lambda) and solved real-world reliability/latency issues with deterministic routing, caching, and query/index optimization. Also built an end-to-end Gmail-based job application tracking agent using a lightweight RAG pipeline with Gemini, strong guardrails (Pydantic schemas, confidence thresholds), and offline regression tests to prevent drift and hallucination-driven data corruption.”

Nithyashree Raghunathan

Screened

Mid-level Software Engineer in Test specializing in AI and healthcare platforms

Santa Clara, CA5y exp

“QA/data pipeline engineer with hands-on AI product building experience, spanning enterprise AWS migration testing for Belgium postal services and personal multi-agent systems in fintech and recruiting. Stands out for combining rigorous validation and production stability work with modern LLM orchestration, guardrails, and messy-document normalization workflows.”

“Engineer focused on AI-assisted and multi-agent software development, with hands-on experience designing structured agent workflows for implementation, testing, validation, and architectural review. Stands out for treating AI as an accelerator rather than a replacement, combining practical experimentation with strong attention to engineering fundamentals and operational concerns like observability, latency, and cost.”

“Backend/AI engineer who has owned production agentic systems end-to-end, including a CRM-integrated multi-agent financial workflow at Wow Payments that cut latency by 83% and achieved 98% uptime. Also built an AI real estate product ('Site IQ') by turning vague stakeholder goals into a geospatial autonomous agent using RAG, rapid prototyping, and tight validation layers around GPT-4 outputs.”