GenAI Optimization Intern

About Modular

At Modular, we're on a mission to revolutionize AI infrastructure by systematically rebuilding the AI software stack from the ground up. Our team, made up of industry leaders and experts, is building cutting-edge, modular infrastructure that simplifies AI development and deployment. By rethinking the complexities of AI systems, we're empowering everyone to unlock AI's full potential and tackle some of the world's most pressing challenges.

If you're passionate about shaping the future of AI and creating tools that make a real difference in people's lives, we want you on our team. You can read about our culture and careers to understand how we work and what we value.

What You Will Work On:

As an intern on the MAX Serve team, you'll tackle real performance problems in state-of-the-art GenAI models like Deep Seek, Llama, and Qwen. You'll execute on a critical project related to performance optimization across the Python/Mojo boundary, working from GPU kernels up through compiler, framework, and multiprocessing optimizations. Your work will involve profiling bottlenecks in multi-billion parameter models, implementing bleeding-edge research (FP8 quantization, speculative decoding, advanced attention), and shipping optimizations to our open-source MAX platform that developers worldwide depend on.

LOCATION:

Candidates based in the United States are welcome to apply. To support growth and collaboration, all interns will work in a hybrid capacity at our Los Altos, CA office (minimum 2 days per week on-site) with relocation assistance provided for out-of-state candidates.

What You Will Learn:

Hands-on experience optimizing GenAI workloads at the intersection of compilers, runtimes, and distributed systems. You'll gain deep expertise in performance optimization techniques, profiling tools, and systems programming while working with Mojo: our next-generation programming language. Mentorship from experienced engineers on the MAX Serve team who work on problems spanning GPU kernels to serving APIs. You'll present and demo your contributions to the engineering organization and make lasting contributions to open-source technology that powers production deployments achieving 200+ tokens/second on multi-GPU systems.

What you bring to the table:

* Currently pursuing a Bachelor's, Master's, or PhD in Computer Science, Engineering, or related field with graduation expected by Spring 2027 at the latest.

* Strong Python programming skills and ML/Deep Learning coursework or projects (PyTorch, Tensor Flow, etc.).

* Passion for performance optimization and systems programming with curiosity for solving complex problems.

* Strong verbal and written communication skills, ability to collaborate with mentors and peers.

* Helpful experience includes: systems programming (C++, Rust), CUDA/ROCm, Python multiprocessing/asyncio, compilers, profiling tools, or parallel computing concepts.

What Modular brings to the table:

* Amazing Team. We are a progressive and agile team with some of the industry's best engineering and product leaders.

* Competitive Compensation. We offer very strong compensation packages, including stock options. We want people to be focused on their best work and believe in tailoring compensation plans to meet the needs of our workforce.

* Team Building Events. We organize regular team onsites and local meetups in Los Altos, CA.

Working at Modular will enable you to grow quickly as you work alongside incredibly motivated and talented people who have high standards, possess a growth mindset, and a purpose to truly change the world.

The estimated base hourly range for this role is $47.00 - $65.00 USD.

The hourly rate for the successful applicant will depend on a variety of permissible, non-discriminatory job-related factors, which include but are not limited to education, training, work experience, business needs, or market demands. This range may be modified in the future.

For candidates who fall outside of the listed requirements, we nevertheless encourage you to apply as we may have openings that are lower/higher level than the ones advertised.