Senior Engineering Manager — AI Inference in Production

crusoe; San Francisco (CA); On-site; USD 250,000 - 300,000; Full time

Benefits offered by this job

Competitive compensation

Equity

Paid time off

Health, dental, vision

401(k) match

Job summary

Crusoe is seeking a Senior Engineering Manager who will lead an ML inference optimization team focused on making large language models run faster, cheaper, and more reliably in production.

You will stay hands‑on with the inference stack while managing the team, delivering end‑to‑end projects, and coordinating with customers to tailor deployments and ensure measurable performance gains.

Qualifications

• 2+ years of experience directly managing and leading an engineering team in a high‑performance or ML‑focused environment.
• Hands‑on experience shipping production code in Python or C++.
• Bachelor’s, Master’s, or Ph.D. in Computer Science, Engineering, Mathematics, or related field.
• Familiarity with ML inference tooling and optimization for high throughput/low latency.
• Experience with modern LLM serving frameworks and performance profiling.

Responsibilities

• Lead team delivery end to end from experiments to production optimizations.
• Profile performance, optimize inference stack, and ensure reliability in production deployments.
• Collaborate with product and customer engineering teams to tailor deployments.
• Balance people management with technical direction and hands‑on coding.
• Communicate complex technical topics clearly to customers and teammates.

Skills

Team leadership

ML infrastructure

Production shipping code

Python

C++

Profiling & optimization

Roadmapping & strategy

Communication with customers

Education

B.S. in Computer Science/Engineering

M.S. or Ph.D. in related field

Tools

Python

C++

CUDA

Docker

Kubernetes

Job description

Crusoe is seeking a Senior Engineering Manager who will lead an ML inference optimization team focused on making large language models run faster, cheaper, and more reliably in production.

You will stay hands‑on with the inference stack while managing the team, delivering end‑to‑end projects, and coordinating with customers to tailor deployments and ensure measurable performance gains.