Member of Technical Staff - ML Performance

Modal
San Francisco, US
On-site

Who this role is best for

Aimed at senior engineers with deep ML performance optimization experience, particularly those comfortable with Nvidia GPU architecture and CUDA in a fast-growing AI infrastructure setting.

Best fit for

  • Senior engineers who have optimized ML systems at scale
    — “strong engineers with experience in making ML systems performant at scale”
  • Candidates with hands-on CUDA and Nvidia GPU architecture expertise
    — “Familiarity with Nvidia GPU architecture and CUDA”
  • Developers who have boosted GPU performance in production ML systems
    — “debugging SM occupancy issues, rewriting an algorithm to be compute-bound, eliminating host overhead”

Things to consider

  • Expect to contribute to open-source projects and Modal’s container runtime
    — “interested in contributing to open-source projects and Modal’s container runtime”
  • Role involves optimizing both language and diffusion models
    — “push language and diffusion models towards higher throughput and lower latency”

How to stand out

  • Prepare concrete examples of ML performance engineering wins
    — “tell us a story about boosting GPU performance”
  • Highlight low-level OS knowledge if applicable
    — “familiarity with low-level operating system foundations”
  • Show experience with torch and high-level ML frameworks
    — “Experience working with torch, high-level ML frameworks”
Pace · Fast PacedCollaboration · MediumAutonomy · MediumDecision Impact · TeamLevel · Senior

Derived from job-description analysis by Serendipath's career intelligence engine.

What success looks like

  • contributing to open-source projects
  • boosting GPU performance
Typical background
5+ years of experience in high-performance code

Skills & requirements

Required

High-quality, High-performance CodeTorchHigh-level ML FrameworksInference EnginesNvidia GPU ArchitectureCUDAML Performance Engineering

Preferred

Low-level Operating System Foundations

Stack & domain

PythonReactTorchHigh-level Ml FrameworksInference EnginesNvidia Gpu ArchitectureCudaMl Performance EngineeringLinux KernelFile SystemsContainersFinanceHealthcare

About the role

This role involves enhancing the performance of ML systems at scale, ideal for an engineer with a knack for optimizing GPU operations and a passion for pushing the boundaries of throughput and latency in AI workloads.

Original posting from Modal via Ashby

ABOUT US:

Modal provides the infrastructure foundation for AI teams. With instant GPU access, sub-second container startups, and native storage, Modal makes it simple to train models, run batch jobs, and serve low-latency inference. We have thousands of customers who rely on us for production AI workloads, including Lovable, Scale AI, Substack, and Suno.

We're a fast-growing team based out of NYC, SF, and Stockholm. We've hit 9-figure ARR and recently raised a Series B https://modal.com/blog/announcing-our-series-b at a $1.1B valuation. Our investors include Lux Capital https://www.luxcapital.com/, Redpoint Ventures https://www.redpoint.com/, Amplify Partners https://www.amplifypartners.com/, and Elad Gil https://eladgil.com/.

Working at Modal means joining one of the fastest-growing AI infrastructure organizations at an early stage, with many opportunities to grow within the company. Our team includes creators of popular open-source projects (e.g. Seaborn https://github.com/mwaskom/seaborn, Luigi https://github.com/spotify/luigi), academic researchers, international olympiad medalists, and experienced engineering and product leaders with decades of experience.

THE ROLE

We are looking for strong engineers with experience in making ML systems performant at scale. If you are interested in contributing to open-source projects and Modal’s container runtime to push language and diffusion models towards higher throughput and lower latency, we’d love to hear from you!

REQUIREMENTS

  • 5+ years of experience writing high-quality, high-performance code.
  • Experience working with torch, high-level ML frameworks, and inference engines (vLLM or TensorRT).
  • Familiarity with Nvidia GPU architecture and CUDA.
  • Experience with ML performance engineering (tell us a story about boosting GPU performance — debugging SM occupancy issues, rewriting an algorithm to be compute-bound, eliminating host overhead, etc).
  • Nice-to-have: familiarity with low-level operating system foundations (Linux kernel, file systems, containers, etc).

Source: Modal careers (Ashby)

Similar roles