Inference Optimization Manager
Modular
United States
Workplace: RemoteFull timeUSD 234,000 - 286,000 annuallyFunction: Software EngineeringExperience: 5+ yearsSkills: ["Leadership","Communication","Team management","Prioritization","Collaboration"]Lead Modular’s Performance Labs to optimize LLM inference across GPU/ASIC architectures, driving state-of-the-art performance while shaping Modular Cloud’s product direction. Manage a high-impact team, collaborate with GTM, Product and Engineering, translate customer workloads into technical roadmaps, and contribute to industry best practices through external thought leadership.
