AIML - Distinguished Engineer, Foundation Model
Core
Designing and optimizing high-throughput inference engines for foundation models to accelerate training, evaluation, and LLM-as-judge workloads.
Role type
Distinguished Engineer (Senior IC with leadership)
Builds
Inference engines and supporting systems for foundation model development
Domain
Artificial Intelligence / Machine Learning / Distributed Systems
Deliverable
production ML models
Required skills
Foundation model inference optimization, distributed systems architecture, GPU/TPU accelerator expertise, model quantization and distillation, ML frameworks (JAX, PyTorch), hardware-aware optimization, technical strategy definition, team leadership, stakeholder alignment
Preferred skills
LLM inference at scale, training loop integration (rollouts, offline eval), Kubernetes and cloud platforms, industry-wide technical strategy shaping
