Lead Engineer, Inference Platform & Scale

Cerebras; Sunnyvale (CA); On-site; USD 150,000 - 200,000; Full time

Benefits offered by this job

Job stability with startup vitality

Open-source AI research

Simple, non-corporate work culture

Job summary

A pioneering AI hardware company in Sunnyvale is looking for an engineering leader to oversee the Inference Service Platform. You will guide a team in scaling LLM inference and architecting low latency systems. Candidates should have substantial experience in distributed systems, strong technical leadership, and a history of optimizing performance. The position emphasizes collaboration across teams to deliver enterprise solutions and requires a hands-on approach to technology and team mentorship.

Qualifications

• 6+ years in high-scale software engineering, with 3+ years leading distributed systems.
• Proven track record scaling LLM inference with optimizations.
• Deep experience with orchestration and large clusters.

Responsibilities

• Own the technical vision for Cerebras Inference Platform.
• Lead development of distributed inference systems.
• Drive operational excellence, ensuring platform reliability.

Skills

Technical Leadership

Inference Expertise

ML Systems Knowledge

Frameworks & Tools

Infrastructure

Operations & Monitoring

Leadership & Collaboration

Tools

Kubernetes

TensorRT-LLM

PyTorch

Hugging Face

Job description

A pioneering AI hardware company in Sunnyvale is looking for an engineering leader to oversee the Inference Service Platform. You will guide a team in scaling LLM inference and architecting low latency systems. Candidates should have substantial experience in distributed systems, strong technical leadership, and a history of optimizing performance. The position emphasizes collaboration across teams to deliver enterprise solutions and requires a hands-on approach to technology and team mentorship.