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 AI Agent engineer to help build our autonomous agent platform and rebuild legacy healthcare workflows with AI Agents at the center. You'll be instrumental in developing AI systems that are already in production, that can understand complex healthcare contracts, read EDI companion guides, utilize tools for navigating highly sensitive healthcare infrastructure, and make intelligent decisions about claims processing - all while maintaining perfect memory of every interaction.

What You'll Work On

• Build and extend the Claim Status Agent - Design intelligent sub-agent architectures that orchestrate multi-route claim lookups (EDI 276/277, payer portals, direct APIs, multiple clearinghouses). You’ll implement recovery strategies that adapt in real-time to payer errors.
• Develop self-enriching context systems - Create memory infra that lets our agents remember what works, which parameter combinations return actionable data, and how to route optimally across thousands of payers
• Fine-tune models and build evaluation frameworks - improve precision, speed and cost on  production traffic processing ~6m claims/year and growing. Design evals that catch regressions before clients do. 
• Expand the agent's capability surface - Integrate new modalities (voice, direct payer connections) and develop techniques for efficiently processing highly varied context across EDI companion guides, payer contracts, PDFs, images, and API outputs

You Might Be a Fit If

• 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 in a team smaller than 10 people
• 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.

Compensation

Meaningful salary and equity available.