Member of Technical Staff, Product

Magic’s mission is to build safe AGI that accelerates humanity’s progress on the world’s most important problems. We believe the most promising path to safe AGI lies in automating research and code generation to improve models and solve alignment more reliably than humans can alone. Our approach combines frontier-scale pre-training, domain-specific RL, ultra-long context, and inference-time compute to achieve this goal.

As a Software Engineer on the Product team, you will build and scale the user-facing systems that sit directly on top of Magic’s long-context models.

This is an end-to-end role spanning frontend, backend, APIs, and deep model integration. You will own product surfaces from problem framing through implementation and iteration, working closely with RL Research & Environments to translate capability improvements into real user impact.

Magic’s long-context models introduce distinct product challenges: making complex behavior understandable, exposing control without overwhelming users, and maintaining reliability under long-running or high-context workloads. You will design systems that make advanced model behavior intuitive and production-ready.

This role can evolve into broader ownership of product architecture, defining AI-native interaction patterns, or leading major product initiatives built on top of Magic’s long-context models.

• Build and maintain web applications and developer-facing tools powered by long-context models

• Design and implement backend APIs and service integrations

• Integrate model capabilities into usable product workflows

• Improve reliability, observability, and performance of product-facing systems

• Collaborate closely with RL and research teams to translate capability gains into shipped features

• Iterate quickly based on product feedback and real-world usage

• Strong software engineering fundamentals across the stack

• Experience building and shipping production-grade products

• High product judgment and strong taste in interaction design

• Ability to translate complex technical systems into simple user workflows

• Comfort operating in ambiguous, fast-moving environments

• Track record of owning product work end-to-end

• Integrity. Words and actions should be aligned

• Hands-on. At Magic, everyone is building

• Teamwork. We move as one team, not N individuals

• Focus. Safely deploy AGI. Everything else is noise

• Quality. Magic should feel like magic