Meta's MTIA (Meta Training & Inference Accelerator) Software team is looking to solve the problem of accelerating Deep Learning and Machine Learning workloads on specialized AI accelerator hardware at datacenter scale by developing high-performance software and hardware technologies.
Requirements
- Experience developing AI training and/or inference software stack
- Experience working with deep learning frameworks such as PyTorch, TensorFlow, JAX, ONNX, MXNet, TensorRT etc
- Knowledge of training deep learning models such as recommendation, ranking, LLM, computer vision, etc
- Familiarity with AI hardware such as GPUs, NPUs, deep learning accelerators is a plus
Responsibilities
- Manage team of domain experts developing AI acceleration software stack for MTIA
- Develop the vision and strategy to help set direction for the team, while managing day-to-day software development
- Communicate and collaborate effectively with peer engineering teams
- Manage a team of developers from a broad range of experiences, perspectives, approaches, and backgrounds, help them develop their careers, assigning them to projects tailored to their skill levels, long-term skill development, personalities, and work styles and resolving conflicts
- Work closely with dedicated recruiting staff to expand the team, including sourcing candidates, interviewing candidates, participating in conferences/events, and on-boarding new employees
- developing AI frameworks to accelerate Meta’s Deep Learning and Machine Learning workloads on the specialized MTIA AI accelerator hardware
- develop PyTorch compiler frontend for MTIA, PyTorch runtime for inference & training, high performance runtime and kernel libraries exploiting various hardware architectural features and tooling
Other
- At least 2 years of experience in managing a software team in a fast-paced capacity
- Demonstrated experience recruiting, building, structuring, leading technical organizations, including performance management
- Individual compensation is determined by skills, qualifications, experience, and location.
