Staff Test & Release Engineer, Inference Cloud (Fully Remote)

d-Matrix; United States; Remote; USD 120,000 - 180,000; Full time

Job summary

d-Matrix is building AI inference infrastructure with a memory-centric architecture, spanning chips to rack-scale systems. You will own end-to-end testing and release management for the Inference Cloud, designing automated E2E tests and ensuring robust deployment strategies across orchestration platforms.

Join a collaborative team focused on hard problems in distributed AI infrastructure, with emphasis on Kubernetes tooling, hardware-in-the-loop testing, and scalable CI/CD workflows.

Qualifications

• 6+ years in test or release engineering for distributed systems.
• Strong Kubernetes, Python/pytest, and CI/CD experience with hardware-in-the-loop testing.

Responsibilities

• Design automated E2E tests for homogeneous and heterogeneous inference deployments.
• Own release strategy, versioning, and rollback for orchestration platform and Kubernetes tooling.

Skills

End-to-end testing

Release engineering

Distributed systems testing

Tools

Kubernetes

Python/pytest

CI/CD

Hardware-in-the-loop testing

Job description

• Own end-to-end testing and release for d-Matrix's Inference Cloud.
• Build test infrastructure on real hardware and enable feature engineers.

Key Responsibilities:

• Design automated E2E tests for homogeneous and heterogeneous inference deployments.
• Own release strategy, versioning, and rollback for orchestration platform and Kubernetes tooling.

What We're Looking For:

• 6+ years in test or release engineering for distributed systems.
• Strong Kubernetes, Python/pytest, and CI/CD experience with hardware-in-the-loop testing.

d-Matrix

d-Matrix builds AI inference infrastructure using a memory-centric architecture, from chips and software to rack-scale systems. The culture values respect, collaboration, direct communication, and execution on hard problems.