AI Agent Engineer — Production-Grade LLM Systems

Starburst; United States; On-site; USD 180,000 - 225,000; Full time

Benefits offered by this job

Equity (ISOs)

Comprehensive benefits

Flexible PTO

Job summary

Starburst is hiring an AI Agent Engineer to design and ship production-grade agent architectures and tooling for enterprise data products. You will build reliable AI agents, handle real-world data quirks, and iterate quickly with an experienced team in a fast-paced environment.

You will push toward measurable improvements in accuracy and task completion while collaborating with researchers to ground and retrieve data. 25% travel is required.

Qualifications

• 5+ years building AI/ML systems, with at least 1 year shipping agentic or LLM-powered systems in production.
• Direct experience at an AI startup or AI-focused product team.
• Hands-on experience with agent frameworks (LangChain, LangGraph, CrewAI, Semantic Kernel, or custom).
• Production RAG pipeline experience (chunking strategies, vector databases, embedding models, reranking).
• Strong software engineering fundamentals: testing, observability, CI/CD, code review discipline.
• Track record of shipping frequently and iterating on user feedback.
• Ability to Travel: This role will require 25% in-person travel for purposes including but not limited to new hire onboarding, team and department offsites, customer engagements, and other company events.

Responsibilities

• Design and build agent architectures: tool orchestration, planning, memory, multi-step reasoning, error recovery
• Ship production-quality agent features with clear ownership from design through deployment
• Close the gap between demo and production: handle partial schemas, inconsistent metadata, mixed data formats, and unreliable source systems
• Introduce proven patterns for agent reliability: structured error handling, fallback chains, observability, guardrails
• Build evaluation suites that catch hallucinations, regressions, and grounding gaps before they reach users
• Collaborate with the AI Research Engineer to integrate grounding and retrieval into agent workflows
• Drive technical standards for agent development through code, not documents
• Turn improvements into measurable gains in task completion rate, accuracy, and time-to-value

Skills

AI/ML systems

Agentic/LLM-powered systems

Agent frameworks

Production RAG pipelines

Software engineering fundamentals

CI/CD, observability

Travel willingness

Tools

LangChain

LangGraph

CrewAI

Semantic Kernel

Job description

Starburst is hiring an AI Agent Engineer to design and ship production-grade agent architectures and tooling for enterprise data products. You will build reliable AI agents, handle real-world data quirks, and iterate quickly with an experienced team in a fast-paced environment.

You will push toward measurable improvements in accuracy and task completion while collaborating with researchers to ground and retrieve data. 25% travel is required.