Engineer - ML + Agent Design

About Chestnut

Chestnut is building the first AI-native operating system for insurance distribution by transforming how the $1T+ insurance industry allocates its largest spend: sales and distribution.

Backed by a16z, we’re replacing legacy systems with a modern, flexible platform that helps carriers automate complex workflows, optimize every distribution dollar, and unlock new growth. We have major insurers under contract, and early adopters are expanding.

This is a generational platform shift. Recent advances in agentic AI make it possible to automate what was once manual and error-prone. We’ve spent years building the data model and context layer required to make this real, and now we’re scaling with urgency.

At Chestnut, we operate with the belief that small, high-context teams working with best-in-class tools and colleagues can achieve outsized results. We embody what it means to be AI-lean: chasing 10x productivity gains that allow us to scale impact beyond our headcount.

If you’re excited to modernize the infrastructure of one of America’s most essential industries, we’d love to meet you. Whether shaping core product experiences or laying the groundwork for intelligent automation, your work will accelerate a once-in-a-generation transformation.

Engineering at Chestnut

We’re building the modern infrastructure for AI-driven insurance operations. That means well-structured data models, real-time event pipelines, clean APIs, and usable tools that support humans and agents working in parallel.

What You'll Do

• Develop and refine ML pipelines for agent behaviors using prompting, fine-tuning, retrieval-augmented generation, and reinforcement learning techniques.

• Prototype and experiment with novel agent reasoning, multi-step planning, and tool usage for complex, data-heavy domains.

• Run structured experiments to evaluate agent performance, optimize reasoning and retrieval, and translate findings into production-ready solutions.

• Build data pipelines and evaluation frameworks that support rapid iteration and deployment of new agent capabilities.

• Collaborate with orchestration and infra teams to ensure agent models are robust, scalable, and reliable in production.

You Might Be a Fit If You…

• Have 3+ years of experience building and analyzing ML systems, including data pipelines, and training frameworks.

• Have strong experience with LLMs, prompting, fine-tuning, and ML experimentation.

• Understand retrieval systems, vector databases, and reasoning techniques for large-scale text datasets.

• Enjoy blending research and engineering to push agent capabilities forward.

• Thrive in fast-paced environments where prototypes quickly evolve into production systems.

Benefits

• Competitive salary and equity, with 10 year exercise window for stock options

• Remote-first culture built on trust, autonomy, and high performance

• Team offsites for all of us to bond

• Take what you need vacation policy

• Top notch health, dental, and vision insurance subsidized by us