Senior Machine Learning Engineer

What you'll do

• Develop, optimize, and productionize machine learning models for the serverless inference platform.
• Build benchmarking and evaluation frameworks to measure latency, throughput, and cost efficiency.
• Improve inference performance using quantization, batching, caching, and accelerator-aware optimization.
• Integrate models into distributed inference infrastructure across a fleet of GPUs and accelerators.
• Drive improvements to model deployment workflows, including validation, rollout safety, and observability.
• Translate customer requirements into scalable machine learning capabilities for Workers AI.
• Mentor engineers and contribute to the technical direction of production ML engineering practices.

What we're looking for

• Develop, optimize, and productionize machine learning models for a serverless inference platform.
• Build benchmarking and evaluation frameworks to measure latency, throughput, and cost efficiency for various model families.
• Improve inference performance using quantization, batching, caching, model compilation, and runtime tuning.
• Integrate models into distributed inference infrastructure across heterogeneous GPUs and next-generation accelerators.
• Drive improvements to model deployment workflows, including validation, rollout safety, and observability.
• Proficiency with Python and modern ML frameworks such as PyTorch, TensorFlow, or JAX (preferred).
• Experience with large-scale inference serving frameworks like vLLM, TensorRT-LLM, or Triton (preferred).
• Authorization to receive software or technology controlled under U.S. export control laws.