Tasks:
- * Analyze end to end performance bottlenecks
- * Build sandbox and rollout services
- * Build traceability for tasks and policy versions
- * Design dynamic resource scheduling
- * Develop extensible runtime interfaces
- * Improve runtime reliability and execution correctness
- * Integrate and optimize inference engines
Perks/Benefits:
Skills/Tech stack required:
[Asynchronous programming] [C++] [Concurrency] [Distributed Systems] [Go] [GPU Profiling] [Isaac Sim] [Kubernetes] [Linux] [Multimodal inference] [Network communication] [Performance Benchmarking] [Python] [Ray] [Reinforcement Learning] [Resource scheduling] [Rollout systems] [SGLang] [Unity] [VLLM]
Educational requirements:
N/A
Role(s):
[AI Infrastructure Engineer] [Distributed Systems Engineer] [Engineer] [Inference Platform Engineer] [Infrastructure Engineer] [Platform Engineer] [Systems Engineer]