We are looking for a Senior Software Development Engineer in Test (SDET) with expertise in AI performance testing, distributed systems, and test automation. The ideal candidate will design scalable performance frameworks, benchmark LLM inference systems, and improve the reliability and efficiency of AI infrastructure.

Key Responsibilities :

- Design and develop reusable automation and performance testing frameworks for AI/ML platforms.

- Benchmark and validate LLM inference engines such as vLLM, SGLang, and TensorRT-LLM.

- Build load-testing solutions using genai-perf, guidellm, llmperf, or equivalent custom tools.

- Analyze AI performance metrics including TTFT, TPOT/ITL, Tokens/sec, Goodput, and p90/p99 latency.

- Collaborate with engineering teams to optimize GPU utilization, system performance, and scalability.

- Develop monitoring dashboards and automated reporting using Prometheus and Grafana.

Required Skills :

- 5+ years of experience in Performance Engineering, SDET, or Test Infrastructure for distributed systems.

- Hands-on experience with LLM inference engines (vLLM, SGLang, TensorRT-LLM).

- Strong programming skills in Python or Go.

- Experience with Kubernetes, CI/CD, containerization, and Infrastructure as Code (IaC).

- Knowledge of NVIDIA CUDA, AMD ROCm, GPU performance metrics, and distributed AI systems.

- Strong understanding of statistical performance analysis, benchmarking, and observability tools.