Note: The job is a remote job and is open to candidates in USA. Modular is a company focused on optimizing inference from kernel to cloud on a unified platform. The Inference Optimization Manager will lead a team to enhance LLM inference performance and collaborate across departments to ensure customer workloads are optimized effectively.

Responsibilities

• Lead the team that builds the optimization platform driving LLM inference on Modular Cloud to state of the art performance across the latest GPU and ASIC architectures
• Own the technical direction of Modular Cloud, delivering LLM performance on the Pareto frontier for agentic use cases and keeping it there as the landscape evolves
• Partner closely with the GTM team to deliver highly customized LLM inference tuned to specific customer workloads, and collaborate across engineering to drive optimizations spanning the full stack, from GPU kernels to cloud infrastructure. Translate insights from customer engagements into a clear technical roadmap that engineering teams can execute against
• Grow and develop a high impact team, set priorities, and create the conditions for engineers to do their best work on hard performance problems
• Champion the team externally through blog posts on innovative approaches to LLM inference optimization that shape industry wide best practices

Skills

• 5+ years in distributed systems or performance engineering, including experience leading or managing engineering teams
• A track record of shipping durable, reusable software tools and libraries adopted across teams and functions, and of guiding a team to do the same
• Sound judgment in evaluating technical tradeoffs and setting priorities, paired with strong communication and technical leadership skills
• The ability to translate ambiguous customer and product needs into focused engineering direction
• Creativity and curiosity in solving complex problems, a collaborative and team oriented mindset, and alignment with our culture
• Hands on background in GPU kernel programming, inference engine internals, or distributed inference architectures
• Experience with Kubernetes and cloud native ecosystems
• Familiarity with modern LLM architectures and the latest inference optimization techniques

Benefits

• Premier insurance plans
• Up to 5% 401k matching
• Flexible paid time off
• Stock options
• Team Building Events
• Regular team onsites and local meetups in Los Altos, CA as well as different cities
• Traveling 2-4 times a year is expected for all roles

Company Overview