Lead Engineer, Senior

• Develop and run long-duration stability tests (MTBF/soak) and stress/fuzzing frameworks.
• Implement fault-injection and recovery validation for runtime and serving layers.
• Build automation pipelines and workload generators for diverse AI models.
• Instrument metrics and observability tools; perform RCA for complex failures.
• Collaborate with cross-functional teams to improve stability and release readiness.

Qualifications

• Bachelor’s/Master’s in CS/EE or equivalent.
  4+ yrs of experience
• Strong systems background: Linux, memory management, concurrency.
• Hands-on with AI inference frameworks (e.g., vLLM, ONNX Runtime, TensorRT).
• Proficiency in Python/C++ for automation and debugging.
• Experience in stability testing, fuzzing, and fault-injection.

Preferred:

• Familiarity with sanitizers (KASAN/ASAN), Valgrind, CI/CD, Kubernetes.
• Knowledge of quantization, PEFT/LoRA, and multi-tenant serving strategies.