Impress employers and recruiters.
Choose from hundreds of resume examples.
Impress employers and recruiters.
Choose from hundreds of resume examples.
Target Resume Now
About the Role
Apple's cloud AI inference platform is rapidly growing, requiring engineering managers to lead teams building components of a complex inference stack. This role is crucial for delivering generative AI inference with verifiable privacy guarantees, operating within Apple's cloud infrastructure.
Responsibilities
- Own a set of components within the inference stack.
- Hire, grow, and lead a team of engineers.
- Own delivery against a roadmap.
- Lead design reviews and make architectural decisions.
- Run on-call and incident management practices.
- Partner across time zones with ML research, hardware, platform, security, privacy, SRE, and product teams.
- Work with teams in London, Cupertino, and Seattle.
- Absorb shifting priorities on behalf of the team.
- Steward APIs and compatibility across versions and hardware generations.
- Reduce cycle time without lowering quality.
Requirements
- Experience managing software engineers, including hiring, coaching, feedback, and performance management.
- Strong software engineering background in systems, backend, distributed systems, or platform work.
- Ability to engage deeply in design trade-offs.
- Demonstrated ownership of delivery on an infrastructure or platform team (roadmap, sequencing, cross-team dependencies, shipped results).
- Agile mindset and track record of operating effectively in ambiguity.
- Ability to absorb rapidly shifting priorities without losing execution discipline or team trust.
- Excellent written communication.
- Effective working habits across geographies and time zones.
- UK/US collaboration experience.
- Genuine security and privacy mindset for systems handling sensitive user content.
- Technical credibility to engage in design reviews and read code.
- Ability to hold your own in a design review.
- Ability to tell a good argument from a confident one.
Skills
- Systems engineering
- Backend engineering
- Distributed systems
- Platform engineering
- Agile methodologies
- LLM inference
- Model serving at scale
- Batching and scheduling
- KV-cache reuse
- Paged attention
- Prefix caching
- Disaggregated serving
- Speculative decoding
- Quantisation
- Model parallelism
- GPU performance
- Custom-accelerator performance
- ML runtime internals
- Framework internals
- Production operations for latency-sensitive services
- SLOs and error budgets
- Observability
- Capacity planning
- Canary and rollback discipline
- Developer experience
- Build infrastructure
- Test infrastructure
- Swift
- C++
- Rust
- Go
- Python tooling
- Privacy-preserving systems
- Security-sensitive systems
- Attested systems
- Reasoning rigorously about logging and measurement
Location
- London
Work Type
- Onsite
Experience Level
- Engineering Manager
About the Company
- Apple's cloud AI inference platform is growing quickly.
- The organisation builds a complex inference stack.
- The generative-AI landscape is rapidly evolving.
- Private Cloud Compute is the system that lets Apple Intelligence reach beyond the device without compromising user privacy.
- It is the server software behind Apple Intelligence.
- The stack includes on-device client frameworks, cloud services for attestation, routing, and orchestration, an inference engine, and model runtimes executing across heterogeneous hardware.
- The platform addresses challenges in context and cache management, model asset management, throughput and latency, observability, and developer/test infrastructure.
- The company values a clear technical direction amidst change and defining roadmaps.
- Collaboration occurs across time zones with various teams.
- The engineering environment is challenging due to privacy constraints that limit usual shortcuts.