Job description

Routing LLM inference at Apple's scale requires systems that adapt to changing demand, available capacity, and failures while maintaining low latency and high utilization. PCC adds a fundamental architectural requirement: request content remains encrypted outside trusted compute nodes. You'll develop routing and scheduling strategies within this privacy model, working with inference and security teams to evaluate techniques such as cache aware request placement and prefill/decode disaggregation. You'll design system architectures, specify custom network protocols and write high performance code. You'll also build scaling strategies for services used by hundreds of millions of people. Our team is small and highly visible, so your chances to make an impact are wide open. If you take opportunities like that and run with them, you'll enjoy working here. You'll own technical decisions from early design through production, using benchmarks and operational evidence to evaluate tradeoffs. You'll work closely with model serving, infrastructure, security, and SRE engineers to turn new inference requirements into reliable routing capabilities. 3+ years of professional experience designing, building and operating large distributed systems in production Server development in Java, C/C++, C#, Go or Swift Knowledge of LLM inference serving, including inference request routing, KV-cache placement and reuse (e.g., prefix-aware routing), prefill/decode disaggregation, and the tradeoffs between latency, throughput and accelerator use Experience with network protocols, application level networking and client-server architectures, including request routing, load balancing or scheduling at scale Experience benchmarking, debugging and tuning the performance of distributed systems, plus knowledge of Unix system internals Experience with cloud deployment and observability technologies such as Kubernetes Bachelor's degree in an engineering related field or equivalent experience Experience building LLM inference serving or routing systems such as llm-d, NVIDIA Dynamo, vLLM, SGLang or similar Familiarity with KV cache aware routing, prefix caching, prefill/decode disaggregation and accelerator capacity placement Experience with TLS, X.509 certificate evaluation or other secure protocols, and awareness of recent developments in standard protocols Understanding of cryptographic protocols, encryption, key management and privacy-preserving system design (e.g., Oblivious HTTP, remote attestation) Experience leading a substantial engineering project from design through production, resolving technical tradeoffs and coordinating across teams. Ability to explain technical tradeoffs, collaborate across engineering teams, and make progress on problems with incomplete requirements.

Requirements

Must-haves

3+ years of professional experience designing, building and operating large distributed systems in production
Server development in Java, C/C++, C#, Go or Swift
Experience with network protocols, application level networking and client-server architectures, including request routing, load balancing or scheduling at scale
Experience benchmarking, debugging and tuning the performance of distributed systems, plus knowledge of Unix system internals
Experience with cloud deployment and observability technologies such as Kubernetes
Bachelor's degree in an engineering related field or equivalent experience
Experience building LLM inference serving or routing systems such as llm-d, NVIDIA Dynamo, vLLM, SGLang or similar
Familiarity with KV cache aware routing, prefix caching, prefill/decode disaggregation and accelerator capacity placement
Experience with TLS, X.509 certificate evaluation or other secure protocols, and awareness of recent developments in standard protocols
Understanding of cryptographic protocols, encryption, key management and privacy-preserving system design (e.g., Oblivious HTTP, remote attestation)
Experience leading a substantial engineering project from design through production, resolving technical tradeoffs and coordinating across teams.
Ability to explain technical tradeoffs, collaborate across engineering teams, and make progress on problems with incomplete requirements.

Nice-to-haves

None flagged.

Application prep

Use the role’s language and application details while tailoring your materials.

Keywords to mirror

llmdesign systemjavagoswiftkubernetes

Platform: apple
Effort: medium

Benefits

Benefits detected in the listing.

Pto