Apple
ML Software Engineer
$142K–$263K
Seattle, Washington · Full-time · Posted Jul 30, 2026
- Experience
- 2 years practical experience plus a bachelor’s degree, or equivalent practical experience.
- Education
- Bachelor’s degree in Computer Science, Computer Engineering, or a related field — or equivalent practical experience.
About the job
Build and improve the ML inference stack for Apple Intelligence’s Private Cloud Compute, coordinating inference across Apple Silicon accelerators and distributed clusters.
What you'll do
- Improve inference-stack stability and performance and implement new functionality from research.
- Bring the inference stack to new SoC generations and platforms in collaboration with hardware, product, and research teams.
- Integrate inference code into a reliable, performant service stack and develop frameworks for coordinating work across accelerators and clusters.
What they ask for
- Experience building large-scale distributed systems serving ML inference, including reasoning about processes, hosts, service tiers, and model behavior under load.
- ML performance mindset, including reasoning about latency/throughput trade-offs and system-level versus model–system co-design.
- Strong in a systems or server language such as Python, Go, Rust, Java, C++, or similar.
- Bachelor’s degree in Computer Science, Computer Engineering, or a related field, or equivalent practical experience.
Nice to have
- Low-level systems, performance, or hardware/SoC bring-up experience.
- Server-side Swift or RPC/networking stacks such as gRPC and Protocol Buffers.
Pay
$142,300 and $263,300 (base salary range)
Tools
Swift, C++, Python, Go, Rust, Java, gRPC, Protocol Buffers
AI focus
Develop and optimize ML inference serving for generative AI, including distributed inference across accelerators and clusters; the posting says the role will not train models.
Model-written summary · the original posting is authoritative