SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Mirror Physics is an NYC-based startup building the AI stack for modern drug discovery. The company develops AI agents that enable scientists to explore, test, and advance new medicines faster and at lower cost. The platform bridges frontier model capabilities with practical challenges in the preclinical drug development pipeline, helping biologists and chemists accelerate their work while maintaining transparency, control, and data security.
As an AI-Native Engineer, you will design, architect, and ship production systems across the full stack—including distributed compute, databases, data pipelines, backend services, user-facing applications, and observability infrastructure. You'll build and improve multi-agent systems, agent harnesses, tool integrations, and inference infrastructure. A key responsibility is developing internal and external benchmarks and evaluations that measure scientific quality, reliability, and usefulness.
You will measure and improve agent quality, cost, latency, and robustness. You'll build repeatable pipelines for integrating and verifying new tools with the traceability required for scientific work. You'll create feedback loops that turn evaluation results and real-world usage into systematic agent improvements. As the company scales, you'll help define Mirror's technical architecture, engineering standards, and hiring bar.
The ideal candidate has exceptional software engineering and system design skills across multiple stack layers. You should have a track record of owning complex projects end-to-end—prototyping quickly, making sound architectural decisions, and turning successful prototypes into reliable production systems. Practical fluency in building, deploying, evaluating, and operating modern AI systems is essential. Strong product judgment, clear thinking, excellent communication, deep curiosity, intellectual honesty, and a consistently high bar for quality are critical. Relevant backgrounds include founding or early-stage engineering roles, building production AI systems at startups, or developing complex systems at larger technology companies.
