Responsibilities
- Apply model optimization methods such as pruning, quantization, and knowledge distillation to support efficient inference on resource-constrained edge hardware and high-volume cloud services.
- Develop high-throughput APIs to encapsulate machine learning models and ensure seamless integration within the larger software architecture.
- Create and manage scalable machine learning frameworks that empower large-scale experimentation by AI researchers.
- Collaborate with AI Scientists to restructure experimental codebases into maintainable, production-deployable systems.
Other
- Benefits are primarily applicable to employees based in the United States.
- For non-U.S. hires, benefit offerings may differ according to local legal requirements, national regulations, and the specific employment entity or platform used.
- The company adheres to a policy of offering reasonable accommodations to qualified individuals with disabilities, as required by applicable laws.
