Machine Learning Research Engineer (MLRE) - GPUs

The role

You will engineer high-efficiency implementations of advanced architectures for foundation simulation models. You will optimize PyTorch and JAX and develop with frameworks like CUDA, Triton, and Warp to accelerate performance critical code.

What you will do

• Profile and optimize PyTorch and JAX without compromising model accuracy, reproducibility, and robustness
• Develop with frameworks like CUDA, Triton, Warp, etc. to accelerate performance critical code sections
• Liaise with NVIDIA to represent needs and implement their tooling
• Work day-to-day with scientists to identify areas of greatest impact
• Travel to SF and NY working groups to collaborate

Required qualifications

• At least two years professional experience in GPU optimization
• Deep understanding of GPU programming fundamentals
• Solid track record of observable artifacts (e.g., GitHub) showing optimization work
• Experience collaborating on software projects across multi-person teams

Nice to have

• Experience working with multi-cloud distributed compute systems
• Experience working with multi-site distributed company team
• Experience working with equivariant architectures that operate on 3-D point clouds

Before you apply

• Travel is part of all roles to conferences and corporate on-site activities

About the company

Achira is building a team of scientists, ML researchers, and engineers to move beyond the beaten path in drug discovery. The company is exploring model architectures for AI x Chemistry to make biology at the molecular level predictable and designable.