ML Software Engineer
Core
Engineer the ML-inference stack for Apple Intelligence's Private Cloud Compute, optimizing performance and stability for generative AI on Apple Silicon datacenter hardware.
Role type
Senior IC ML Software Engineer (Inference Stack)
Builds
Private Cloud Compute inference stack for Apple Intelligence
Domain
Cloud infrastructure + Generative AI
Deliverable
production ML models
Required skills
Distributed systems, ML inference optimization, Systems programming (C++/Python/Go/Rust), Hardware/SoC integration, Observability, Concurrency management
Preferred skills
Server-side Swift, RPC/networking stacks (gRPC, Protobuf), Low-level systems programming, GPU acceleration, Production incident management
Technologies
Swift, C++, Python, Go, Rust, gRPC, Protocol Buffers, OpenTelemetry, Splunk, XPC, Instruments
Responsibilities
Engineer continuous improvements in stability and performance for the inference stack, implement new functionality from research, integrate inference code into the full service stack, collaborate with hardware and research teams.
Seniority
Senior, hands-on IC
