AI Inference Core

Responsibilities

• Design, develop, and maintain automated test frameworks, tools, and infrastructure for AI inference software.
• Own integration testing and qualification activities for complex inference-core features, including dependency, interaction-risk, and coverage analysis.
• Develop and execute end-to-end, integration, regression, and system-level tests across frameworks, runtime, compiler, kernels, infrastructure, and hardware.
• Analyze test and benchmark results to assess release readiness and provide qualification recommendations.
• Investigate cross-stack failures, perform root cause analysis, collaborate on fixes, and implement regression-prevention tests.
• Improve master and release-branch stability through regression identification, failure triage, fix validation, and quality metrics.
• Build tooling for automation, diagnostics, monitoring, dashboards, CI/CD workflows, and release qualification pipelines.
• Contribute to test architecture, risk-based testing strategies, observability, automation efficiency, and release reliability.
• Provide technical guidance and mentorship to junior engineers through reviews and debugging sessions.

Requirements

• Professional experience developing software, automated testing frameworks, or test infrastructure.
• Proficiency in Python, Go, or a similar programming language with experience writing maintainable production-quality code.
• Experience designing, developing, and maintaining automated tests and frameworks for complex software systems.
• Strong debugging and problem-solving skills, including log analysis, system-behavior investigation, and root cause identification.
• Understanding of integration, system, regression, and end-to-end testing methodologies.
• Experience with CI/CD pipelines, test automation infrastructure, and software development workflows.
• Working knowledge of operating systems, networking, distributed systems, or systems-level software.
• Ability to independently own complex technical problems and drive issues through resolution.
• Strong communication and collaboration skills across multiple engineering teams.
• Preferred: experience with distributed systems, infrastructure software, runtime systems, compilers, kernels, AI/ML infrastructure, LLM inference, model deployment, multimodal workloads, hardware accelerators, GPU systems, or high-performance computing.
• Preferred: experience building scalable test frameworks, distributed test systems, release pipelines, or internal developer tools.
• Preferred: familiarity with performance testing, profiling, observability, fault injection, reliability engineering, production failure analysis, containers, Kubernetes, cloud infrastructure, or cluster orchestration.

Benefits

• Hybrid schedule with at least three days per week in the office; fully remote work is not available.
• Office locations are Sunnyvale, California, or Toronto, Ontario.
• Opportunity to work on a breakthrough AI platform, AI supercomputing, and cutting-edge AI research and open-source projects.
• Inclusive equal-opportunity workplace with continuous learning, growth, and team support.