AWS Cloud Inference Engineering Lead

Polluxa, Inc.; San Francisco (CA); On-site; USD 180,000 - 270,000; Full time

Job summary

Polluxa, Inc. seeks an Engineering Manager to lead the Cloud Inference team for AWS, owning Claude on AWS end-to-end from API to deployment. You will drive scale, performance, safety and security while advancing packaging, testing and deployment infrastructure globally.

You will set strategy, hire and coach high-caliber engineers, collaborate across teams, and travel frequently between Seattle and the SF Bay Area to align with partners and stakeholders in a fast-paced AI space.

Qualifications

• 10+ years in high-scale software development, infrastructure or capacity management.

Responsibilities

• Set technical strategy and oversee development of Claude on AWS across all layers of the technical stack.
• Collaborate with teams to understand product, infrastructure, operations and capacity needs.
• Work with stakeholders to align on goals and drive outcomes.
• Create clarity in a fast-changing environment.
• Hire and coach top technical talent, supporting a high-performing team.
• Design and run postmortem reviews, incident response, and on-call rotations.

Skills

High-scale infra

Capacity mgmt

Engineering mgmt

Recruiting

Scaling ops

AI safety focus

Stakeholder alignment

10+ yrs exp

Tools

GPUs

TPUs

NCCL

Trainium

Job description

Polluxa, Inc. seeks an Engineering Manager to lead the Cloud Inference team for AWS, owning Claude on AWS end-to-end from API to deployment. You will drive scale, performance, safety and security while advancing packaging, testing and deployment infrastructure globally.

You will set strategy, hire and coach high-caliber engineers, collaborate across teams, and travel frequently between Seattle and the SF Bay Area to align with partners and stakeholders in a fast-paced AI space.