Harness Engineer

About Substrate

Substrate (www.substrate.cc) is building the world’s first AI native BPO, starting with healthcare RCM. We’re focused on helping healthcare enterprises like physician groups, EMR providers, and BPOs accelerate AR, and get reimbursed quickly and cost effectively. We already touch over 500k healthcare claims each month.

The Role

We're looking for an exceptional Harness Engineer to help build the systems around our agents and AI products. You'll be instrumental in advancing AI systems that are already in production, and improving success rates for probabilistic products, and precision for deterministic ones. You’ll build systems that can understand complex healthcare contracts, read EDI companion guides, utilize tools for navigating highly sensitive healthcare infrastructure and banking/financial infrastructure, and make intelligent decisions about claims processing - all in service of helping healthcare providers get paid fairly.

What You'll Work On

• Build and extend our suite of agents - Design agents and the systems around them to do a variety of tasks for healthcare practices, including monitoring claims, reviewing payer policies, determine medical necessity, iterate through messy provider data, reconcile payments, and more.

• Deploy agents and the systems around them - Partner with clients and prospects on frontier use cases, getting agents to work safely in extremely sensitive environments.

• Develop high quality measurement infrastructure: improve how we measure and track agent and model behavior, increase precision, and build systems to help optimize speed, and cost on production traffic touching tens of millions of claims each year.

• Adapt with the nature of work: How work gets done is changing. Individuals have enormously more leverage than ever before. A big part of the role (and all roles at Substrate) is exploring how to be more effective, efficient and leveraged as the toolscape evolves rapidly around us.

You Might Be a Fit If

• You’ve been load bearing in previous roles, and are willing to take an extreme amount of ownership.
• You are interested in going deeper into problems than anyone reasonable would, in service of excellence.
• You have a track record of independently building and shipping ML/AI products that solve real business problems
• Deep experience with modern LLM architectures, fine-tuning approaches, and utilizing evals at scale
• You either have healthcare domain knowledge already, or you’re excited about using AI to automate the tedium in healthcare
• You’ve either started a company before, launched and scaled independent products, or have been an early startup engineer
• You are both proficient as a software engineer in the traditional sense, and you've fully adopted coding agents into your workflow.
• You’re excited about working in person, in San Francisco, 3 days a week.

Some general color on what we’re looking for: https://writing.kunle.app/p/come-work-with-me-at-substrate .

We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed. If you spike extremely in certain areas or not in others, or if you’re extremely interested in this work and willing to go very deep to create something special, please apply and lets chat.

Compensation

Meaningful salary and equity available.

• We want you to show us something you've built. It can be completely by hand or it can be completely AI-generated, but we want you to explain exactly how it was built, show us what prompts you used, and in particular why you picked this problem to solve, and show us the results.
• Your technical interview will feature both a pure technical part that evaluates your coding abilities and your ability to write and review code, and an AI-assisted part that shows how you are adopting AI technologies in your coding practice and what benefits you've gotten from them.