Responsibilities
- Design and implement a high-performance inference framework optimized for scale
- Deploy and maintain software on the world's largest supercomputing and data infrastructure
Requirements
- Bachelor of Science or equivalent experience in Computer Science or Software Engineering
- Eight years of professional experience in modern C++, C, or Rust
- Three years working in Linux environments with proficiency in development tools
- In-depth understanding of the TCP/IP network protocol stack
- Strong grasp of computer architecture and operating system principles
Nice to Have
- Practical experience with large language model inference systems
- Proficiency with distributed storage solutions
- Knowledge of Linux internals and low-level optimizations including benchmarking, bottleneck analysis, and performance tuning
- Experience writing CUDA kernels is a plus
- Background in parallel computing, high-performance computing, or RDMA technologies
Benefits
- Work alongside leading experts in the field
- Performance-driven compensation structure
- Chance to contribute to transformative technology used globally
- Competitive salary offerings
- Extensive benefits package including health, wellness, and retirement
Compensation
Aggressive compensation plan with highly competitive salaries
Work Arrangement
Not specified
Team
Collaborative environment working alongside industry leaders
Other
- Dedicated to cultivating a diverse and inclusive workplace
- Proudly maintains an equal opportunity employer status
- Prohibits discrimination based on race, religion, color, national origin, gender, gender identity, sexual orientation, age, marital status, veteran status, disability, or any other legally protected characteristic
Not specified