AI Framework Engineer - QA & Benchmarking

Key Responsibilities Agentic QA Automation: Help design and build automated QA flows using LLMs/Agents to catch, triage, and report framework and hardware bugs with minimal manual effort. Benchmarking and Validation: Run, maintain, and expand end-to-end (E2E) benchmarks, unit tests (UT), and microbenchmarks for PyTorch, vLLM, and SGLang. Hardware and Stack Coverage: Validate latency, throughput, and functionality across different hardwares; track and reproduce performance regressions. Issue Tracking and CI/CD: Maintain test tracking sheets, document bug reproduction steps, and integrate tests into CI/CD pipelines.

Basic Qualifications Education: Bachelor, Master, Software Engineering, or a related field Programming: Proficient in Python AI/ML Fundamentals: Basic understanding of Deep Learning concepts, Transformer models, and standard model execution flow. Linux and Tools: Comfortable working in Linux environments, using shell scripting (Bash), and version control with Git. Preferred Skills (Nice to Have) Hands-on experience or coursework with PyTorch, vLLM, or SGLang. Experience building basic LLM applications, scripts, or agent workflows (e.g., using LLM APIs or frameworks like LangChain). Exposure to basic testing concepts (UT, regression testing) or CI/CD tools (e.g., GitHub Actions). Familiarity with Docker or profiling tools (e.g., PyTorch Profiler).

College Grad

Shift 1 (China)

PRC, Shanghai

All qualified applicants will receive consideration for employment without regard to race, color, religion, religious creed, sex, national origin, ancestry, age, physical or mental disability, medical condition, genetic information, military and veteran status, marital status, pregnancy, gender, gender expression, gender identity, sexual orientation, or any other characteristic protected by local law, regulation, or ordinance. Position of Trust N/A