Inference Systems Engineer for Transformers & Low-Latency HPC

Etched; San Jose (CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Medical, dental, and vision packages

Housing subsidy of $2k per month

Relocation support for those moving to San Jose

Daily lunch + dinner in the office

Job summary

An innovative AI hardware company in San Jose is looking for talented engineers to support the porting of state-of-the-art AI models to their architecture. Candidates should be proficient in C++ or Rust and have a strong understanding of performance-sensitive distributed software systems. This full-time position offers competitive benefits including a housing subsidy and wellness programs designed to support team members both professionally and personally. Join the team committed to redefining AI infrastructure.

Qualifications

• Proficiency in C++ or Rust.
• Understanding of complex distributed software systems like Linux internals and accelerator architectures.
• Familiarity with deep learning frameworks such as PyTorch or JAX.

Responsibilities

• Support porting state‑of‑the‑art models to our architecture.
• Build, enhance, and scale Sohu’s runtime for multi‑node inference.
• Utilize performance profiling tools to identify bottlenecks.

Skills

Proficiency in C++ or Rust

Understanding of performance-sensitive distributed software systems

Familiarity with PyTorch or JAX

Job description

An innovative AI hardware company in San Jose is looking for talented engineers to support the porting of state-of-the-art AI models to their architecture. Candidates should be proficient in C++ or Rust and have a strong understanding of performance-sensitive distributed software systems. This full-time position offers competitive benefits including a housing subsidy and wellness programs designed to support team members both professionally and personally. Join the team committed to redefining AI infrastructure.