Summary by AIEngineer.careers
Senior Machine Learning Engineer is a ML Infrastructure Engineer role (full-time). with Apple. in CUPERTINO, CA, US. Compensation shown: $185K–$325K. Imported listing (source: mindpal.co). Apply on the employer's site (mindpal.co).
Imported listing (source: mindpal.co) · Apply on mindpal.co
How our listings work
The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.
Imported job description
Sourced from mindpal.co
Apple is hiring a senior/staff-level engineer to build distributed AI execution frameworks spanning large-scale model training, post-training, reinforcement learning, and high-performance LLM inference. The role focuses on scalable execution, developer-facing APIs/SDKs, and runtime optimizations across heterogeneous hardware. You will partner with AI researchers and product teams to translate model requirements into reusable, production-quality capabilities.
Responsibilities
- Design and build scalable distributed AI execution frameworks for training, post-training, RL, and inference using Ray
- Develop high-level APIs/SDKs and reusable workflows for fine-tuning, preference optimization, and reinforcement learning
- Optimize LLM inference runtimes for cost, latency, throughput, and resource efficiency
- Implement runtime optimizations across GPU execution, memory, kernels, communication, batching, and KV-cache management
- Evaluate and integrate modern inference/training engines such as vLLM and SGLang
- Design distributed execution strategies including parallelism, workload placement, and communication efficiency
- Improve reliability via fault tolerance, checkpointing, observability, and performance diagnostics
- Establish benchmarks for training efficiency, inference latency/throughput, and cost per token
Requirements
- 6+ years building distributed systems, AI platforms, model execution frameworks, or high-performance software
- Hands-on experience in large-scale AI training, LLM post-training/RL, or LLM inference and serving optimization
- Proficiency in Python and a systems-level language such as C++, Rust, Go, or Java
- Experience with PyTorch and modern foundation model architectures
- Understanding of distributed parallelism strategies (data, tensor, pipeline, expert)
- Ability to profile and optimize AI workloads across GPUs/accelerators
- Experience building APIs/SDKs or reusable components for AI model development and deployment
- Experience with Ray or comparable distributed execution frameworks
- Strong software design, debugging, and performance analysis skills
- B.S./M.S./Ph.D. in CS/AI or related field, or comparable experience
Nice to Have
- Contributions to open-source distributed AI systems such as Ray
- Experience with TensorRT-LLM, quantization, speculative decoding, or disaggregated prefill/decode
- Familiarity with Kubernetes and multi-model serving
Tech Stack
C++DeepSpeedDistributed SystemsFSDPGoGPU OptimizationJavaKubernetesLLMPythonPyTorchRayReinforcement LearningRustSGLangTensorRT-LLMvLLM

Cupertino · US · 223517+ employees
Apple is a global leader in designing, manufacturing, and marketing smartphones, personal computers, tablets, wearables, and accessories. The company also provides a variety of related digital services, software, and content platforms.