Software Engineer, AI Agents

We are looking for a product-minded software engineer to help build the infrastructure and the intelligence layer for the future of healthcare operations.

This is a full-stack role working on all parts of the product. You will work across voice agents, LLM orchestration, browser automation, agent integrations, and build the interfaces customers use to interact with their agents.

What you’ll do

• Design and develop AI agents that work across all modalities of phone, sms, and computer use.
• Build evaluation and observability systems that make our agents predictable in every task.
• Optimize the core performance of our agent infrastructure for environments that need super low latency.
• Contribute to technical planning.
• Help establish the engineering practices needed to grow an engineering organization.
• Work directly with healthcare operators to understand their workflows and translate those into agentic solutions.

What we’re looking for

• Strong software engineering fundamentals, particularly in backend or full-stack development. We care more about what you have built and how you approach difficult problems more than certifications, education or coding languages.
• Ability to experiment and execute with speed. The faster we iterate, the more we can help our customers realize the full potential of AI.
• Experience shipping and operating production systems.
• Comfortable with owning ambiguous problems and engineering dependable solutions.
• Experience building with LLMs and agent frameworks, or the ability to learn this area quickly.
• Clear written and verbal communication. Everyone at Shasta works directly with customers.

Particularly relevant experience

Any of the following would be helpful, but none is individually required:

• Early-stage startup experience or meaningful ownership of a product from zero to production
• Conversational AI, telephony, or real-time communication systems
• Chat systems
• Healthcare EMRs, insurance eligibility, prior authorization, or revenue-cycle operations
• Long-running jobs and workloads
• LLM evaluation, observability, and agent reliability