Software Engineer, AI Inference
Core
Optimizing AI inference pipelines and infrastructure for real-world robotic deployment, ensuring efficient operation of embodied systems under variable compute and hardware constraints.
Role type
Senior IC software engineer (AI inference optimization)
Builds
Runtime AI inference pipelines, frameworks, and tooling for robotic systems
Domain
Robotics + Machine Learning
Deliverable
production ML models
Required skills
Low-level systems languages (C, C++, Rust, Go), Python, deep learning libraries (PyTorch, TensorFlow, JAX), CUDA, multithreading, networking, embedded systems, memory management, machine learning compilers, model inference optimization
Preferred skills
Experience with autoregressive, denoising, hierarchical models, state machines, multi-agent systems, cloud-based inference, adapting solutions to hardware constraints
Technologies
CUDA, PyTorch, TensorFlow, JAX, C, C++, Rust, Go
Responsibilities
Develop and optimize runtime AI inference pipelines for real-world robotic deployment; Build infrastructure, frameworks, and tooling to enable reliable integration of models into robotic systems; Formulate specialized optimization solutions for various inference paradigms and scenarios; Adapt optimization solutions to various compute, hardware, and networking constraints
Seniority
Senior, hands-on IC
