Software Engineer, ML Accelerators

DeepMind is building a next-generation compute platform that pairs ML hardware acceleration with software and hardware co-design. In this onsite role in Mountain View, you will work on the ML compiler stack and inference infrastructure that translates AI workloads into high-performance execution across low-level hardware operators.

This Software Engineer position is centered on designing and developing the software components needed for fast, reliable inference, while collaborating closely on performance tuning and debugging that spans both software and hardware.

Key Responsibilities

• Own a full-stack software role focused on the ML compiler and inference infrastructure.
• Design and develop an ML compiler stack that bridges AI workloads with low-level hardware operators.
• Design and develop software infrastructure aimed at enabling high performance inference.
• Contribute to software and hardware co-design, including kernel optimization, performance tuning, and debugging.

Required Qualifications

• Bachelor’s degree in Computer Science, a related technical field, or equivalent practical experience.
• Experience in software development using Python and C++.
• Experience with machine learning hardware accelerators, ML compiler stacks (for example, JAX, PyTorch, XLA), and kernel development.

Preferred Qualifications

• PhD degree in Computer Engineering, Computer Science, or a related field.
• 2 years of experience in full-stack system development for hardware accelerators.
• 2 years of experience building collaborative, hyper-scalar software and applying engineering best practices.
• Experience scoping, planning, and executing projects toward team goals in ambiguous environments.

Technology Focus

• Python
• C++
• JAX
• PyTorch
• XLA

Location: Mountain View, CA (onsite)
Compensation: USD 174,000 - 252,000 per year