onsite
Machine Learning Architect, Platform Architecture - Apple
ML Engineer
Lead the design of machine‑learning solutions tightly integrated with Apple silicon, driving performance and efficiency across SoC, system, and software layers.
About the role
Key Responsibilities
- Architect end‑to‑end ML pipelines that run efficiently on Apple silicon, balancing compute, memory, and power constraints.
- Collaborate with SoC/IP, system, and software teams to define hardware‑software interfaces and data paths for ML workloads.
- Develop and validate performance models, conduct profiling, and iterate on hardware and software optimizations.
- Define and enforce best practices for ML algorithm deployment, quantization, and model compression on embedded platforms.
- Mentor cross‑functional teams, provide technical guidance, and influence product strategy around ML capabilities.
Requirements
- Advanced degree (MS/PhD) in Computer Science, Electrical Engineering, or related field with focus on ML or hardware architecture.
- 5+ years of experience designing ML systems for embedded or SoC environments.
- Deep knowledge of Apple silicon architecture, GPU/Neural Engine programming, and low‑level performance tuning.
- Proficiency in C/C++, Python, and hardware description languages (e.g., Verilog/VHDL) for prototyping.
- Strong analytical skills, ability to translate complex requirements into scalable, high‑performance solutions.