AIML - Sr Machine Learning Engineer, Evaluation
Core
Design and develop evaluation infrastructure, benchmarks, and simulation environments to refine Apple's foundation models and agents.
Role type
Senior IC machine learning engineer (evaluation & refinement)
Builds
Evaluation pipelines, LLM judges, reward models, simulation environments, and optimization tools for AI agents
Domain
Artificial Intelligence / Large Language Models / Agentic Systems
Deliverable
production ML models
Required skills
Machine learning systems, distributed infrastructure, LLM evaluation, reward modeling, prompt optimization, simulation environments, trajectory-based data generation, Python, PyTorch
Preferred skills
LLM-as-judge, post-training (SFT, DPO, RLHF), agentic systems, on-device ML, privacy-preserving ML
Technologies
PyTorch, Python
Responsibilities
Design and build evaluation infrastructure for agents and foundation models; develop LLM judges and reward models; build simulation environments for agent evaluation; collaborate with product teams to address quality gaps; contribute datasets and reward signals to post-training loops
Seniority
Senior, hands-on IC
