California SoftTech, Inc.
Machine Learning Engineer
- Location
- US
- Employment
- Full Time
Job summary
This is a hands-on training engineer who also knows the GPU platform underneath. It is not an SRE role and not an MLOps/GenAI architect role. Must show on the resume (reject if missing): • Multi-node distributed training they ran and debugged personally, with PyTorch FSDP, DeepSpeed, Megatron or NeMo • Ray Train • Kubernetes on Google Cloud Platform (GKE) with GPU node pools, plus job queueing (Kueue or similar) and quota/capacity management • GPU networking: NCCL tuning, RDMA/GPUDirect, multi-…
SalaryCheck the source listing for salary
General interview preparation
General preparation guidance from MiPrep; these interview stages are not confirmed for this job.
- Recruiter phone screen - typically 20-40 min
- Technical screen - 1 coding problem or take-home; format varies by company
- Onsite / virtual loop - typically 4-6 rounds over 2-3 weeks; exact split of coding, systems design, and behavioral varies by role and location