Description

You will develop a highly optimized inference framework running on large-scale supercomputers and data centers.

This role is remote.

Responsibilities

• Develop high-performance inference frameworks.
• Implement low-level optimizations for data center infrastructure.
• Analyze and resolve performance bottlenecks in production systems.
• Contribute to the design and implementation of next-generation networking features.

Required Skills

• 6+ years of experience in modern C++, C, or Rust development.
• 3 years of experience working in a Linux environment.
• Deep knowledge of the TCP/IP network stack.
• Understanding of computer architecture and operating system concepts.
• Experience with parallel programming or high-performance computing.
• Familiarity with development tools.

Preferred Skills

• Background in Linux internals and low-level software optimizations.
• Experience programming CUDA kernels or familiarity with ML frameworks/LLMs.
• Knowledge of RDMA technology.

Key Skills

Education

Any Graduate