Principal Software Engineer
Core
Designing, optimizing, and debugging high-performance software systems and end-to-end inference pipelines for state-of-the-art LLMs.
Role type
Principal Software Engineer (High Performance Computing & LLMs)
Builds
High-performance inference systems and optimized software pipelines for LLMs
Domain
Artificial Intelligence / Large Language Models / High Performance Computing
Deliverable
production ML models
Required skills
C, C++, C#, Java, JavaScript, Python, GPU architecture, CPU architecture, HW neural net acceleration, GPU profiling tools, end-to-end performance analysis, software engineering principles
Preferred skills
Experience with OpenAI or similar state-of-the-art LLMs, experience with HPC applications
Responsibilities
Create, implement, optimize, debug, refactor, and reuse code to improve performance and maintainability; Act as a Designated Responsible Individual (DRI) to guide engineers and drive project/release plans; Monitor systems for degradation or downtime and initiate restoration actions; Identify and drive improvements to end-to-end inference performance of LLMs; Speed up and reduce complexity of key components/pipelines to improve system efficiency
