ML Engineer - Infrastructure
Core
Design, bring-up, operation, and optimization of performant GPU clusters for training foundation models for humanoid robots.
Role type
Senior ML Engineer (Infrastructure)
Builds
Cloud-based GPU clusters and compute platforms for AI model training
Domain
Robotics / Distributed Systems / Cloud Infrastructure
Deliverable
infrastructure
Required skills
Distributed training (DDP, FSDP, NCCL), Python, PyTorch, Job scheduling (Slurm, Kubernetes/KubeRay), Cloud platforms (AWS, GCP, Azure), Profilers, Multi-cloud strategy
Preferred skills
High-performance file systems (Lustre), Infrastructure-as-code (Terraform, Ansible), Multi-cloud provisioning
Responsibilities
Architect and optimize cloud-based GPU clusters; Help AI engineers optimize training workloads and hardware utilization; Contribute to GPU compute strategies; Optimize capacity and cost via multi-cloud strategies; Raise engineering practices (testing, code quality, reliability)
Seniority
Senior, hands-on IC
