AI-Native Engineer

THE COMPANY Mirror is an NYC-based startup building the AI stack for modern drug discovery. We develop agents that give scientists the leverage to explore, test, and advance new medicines faster and at lower cost. Our platform focuses on bridging the gap between frontier model capabilities and the practical challenges faced by biologists and chemists across the preclinical pipeline to dramatically accelerate scientists’ daily work, without sacrificing transparency, control, or data security. By compounding advancements in agent performance, efficiency, and reliability, we’re paving the way to transforming therapeutics development and unlocking a new era of human health. THE OPPORTUNITY We’re an AI-native company. Achieving efficiency and scale by leveraging AI is both what our customers pay us for and a priority for every employee. As such, nearly everything we build is an AI system, not a one-off solution. We need full-stack engineers with a deep understanding of traditional software development as well as a strong command of how to use and deploy the modern AI stack. Drug discovery is a rich field driven by experts with deep knowledge, experience, and taste. As a lead engineer, you’ll help us build the highest-quality platform for these experts, as well as the surrounding systems that enable scale without sacrificing rigor or reliability. WHY THIS ROLE There are remarkably few opportunities for software engineers to work on interesting problems that tangibly impact a meaningful mission of significant scale. We’re building solutions for scientists at the front lines of translating capital into therapeutics—not as a research project, but with all of the practical constraints involved in bringing drugs to the clinic (i.e., to humans whose lives they might improve). When we succeed, it’s because we’ve created value for those scientists and substantially advanced their efforts. WHAT YOU’LL DO - Design, architect, and ship production systems across the stack, including distributed compute, databases and data pipelines, backend services, user-facing applications, and observability infrastructure. - Build and improve multi-agent systems, agent harnesses, tool integrations, and inference infrastructure. - Develop internal and external benchmarks and evaluations that measure scientific quality, reliability, and usefulness. - Measure and improve agent quality, cost, latency, and robustness. - Build repeatable pipelines for integrating and verifying new tools, with the traceability required for scientific work. - Create feedback loops that turn evaluation results and real-world usage into systematic agent improvements and keep benchmark sets current. - Ship new harness, interface, and enterprise capabilities, and automate high-leverage internal workflows as company priorities evolve. - Help define Mirror’s technical architecture, engineering standards, and hiring bar as the team grows. WHAT WE’RE LOOKING FOR -…