Inference Optimization Engineer

Modular•United States / Canada,

2d•$198,000 - $286,000•Hybrid

About The Position

At Modular, we optimize inference from kernel to cloud on one unified stack. We are building a differentiated cloud platform that delivers state of the art inference performance from day one, then keeps getting better. As we learn the shape and patterns of each customer's workload, the platform adapts and improves performance automatically over time. The Performance Labs team builds the infrastructure that makes this possible at scale. We continuously apply the latest optimizations across kernels, the inference engine, and distributed systems so that customer workloads stay on the Pareto frontier of cost and performance. We get there through deep workload insights, a scalable platform, and close collaboration with engineering and product teams. In this role you will dig into real customer inference workloads, profile them end to end, and apply the optimizations across kernels, engine, and distributed systems that push each workload toward the Pareto frontier. You will build the tooling and platform that turns one off performance wins into a repeatable, automated optimization loop, and you will work directly with engineering, product, and GTM to bring those gains to customers in production.

Requirements

5+ years of experience in distributed systems or performance engineering.
A track record of building durable, reusable software tools and libraries that are adopted across teams and functions.
Sound judgment in evaluating technical tradeoffs and setting priorities, paired with strong communication and technical leadership skills.
Creativity and curiosity in solving complex problems, a collaborative and team oriented mindset, and alignment with our culture.

Nice To Haves

Experience with 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.

Responsibilities

Build the optimization platform that drives inference performance of LLMs served on Modular Cloud to state of the art levels across the latest GPU and ASIC architectures.
Shape 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 use cases, and collaborate across engineering to drive optimizations spanning the full stack, from GPU kernels to cloud infrastructure.
Translate insights from customer engagements into technical direction for engineering teams.
Publish blog posts on innovative approaches to LLM inference optimization that shape industry wide best practices.