Apple
Sr. Machine Learning Engineer, Foundation Models Inference - Cloud OS & Inference
$175K–$325K
Santa Clara, California +1 · Senior · Full-time · Posted Aug 13, 2026
- Location
- Santa Clara, California
Seattle, Washington - Experience
- 5+ years leading complex, ambiguous technical projects end to end.
- Education
- BS in Computer Science, Machine Learning, Artificial Intelligence, Data Science, or a related field.
About the job
Build and optimize secure, privacy-preserving foundation-model inference systems for high-throughput, low-latency deployment at Apple scale.
What you'll do
- Optimize inference for language, vision, and speech model architectures with the Foundation Model Research team and external partners.
- Design and ship production inference systems; build profiling tools and simulators to find performance bottlenecks.
- Drive technical decisions for large-scale serving and mentor engineers.
What they ask for
- 5+ years of experience leading complex, ambiguous technical projects end to end.
- Hands-on experience with LLM inference stacks and working knowledge of GPU or TPU programming concepts.
- Proficiency with PyTorch, JAX, or TensorFlow; experience operating high-throughput services at large distributed scale.
- Experience deploying applications on cloud platforms (AWS, GCP, or equivalent) using Kubernetes and Docker; BS in a related field.
Nice to have
- Experience building production systems in Go or Python; knowledge of deep learning architectures including Transformers and multimodal variants.
- Experience with inference optimization frameworks or custom CUDA kernels; MS in a related field.
Pay
$175,000 and $308,500 USD base salary; $184,700 and $324,800 USD base salary
Tools
PyTorch, JAX, TensorFlow, AWS, GCP, Kubernetes, Docker, Go
AI focus
Optimize and deploy language, vision, and speech foundation-model inference, including efficiency, hardware/software codesign, and production serving.
Model-written summary · the original posting is authoritative