Senior System Software Engineer

Job Summary

To support the development of a Generative AI inference platform, the full-time Senior System Software Engineer will create open source software for GPU-accelerated inference of trained AI models, contributing to disaggregated serving capabilities and innovating inference-state management for long-running agents.

Key responsibilities:

• Develop open source software for AI model inference on GPUs
• Enhance Dynamo's distributed inference frontend and support new models and request parameters
• Optimize software components for distributed inference workloads while balancing performance and resource management

Required qualifications:

• Masters or PhD in Computer Science, Computer Engineering, or equivalent experience
• 10+ years of relevant experience in a related field
• Proficiency in Rust/Python programming and software design
• Familiarity with modern LLM API semantics
• Ability to work effectively in a fast-paced, agile team environment