We are looking for a Senior FDE with strong expertise in AI infrastructure, GPU clusters, Kubernetes, and distributed systems to work directly with customers on production AI workloads.
Key Responsibilities
- Design and optimize GPU infrastructure and LLM inference platforms.
- Work with NVIDIA/AMD GPUs, CUDA/ROCm, vLLM, TensorRT-LLM, and SGLang.
- Deploy and manage Kubernetes-based AI infrastructure.
- Automate infrastructure using Terraform, Ansible, and Helm.
- Troubleshoot GPU drivers, NCCL/RCCL, networking, and storage issues.
- Collaborate directly with customer engineering teams to deliver production AI solutions.
Required Skills
- 6+ years of experience in AI Infrastructure, FDE, Distributed Systems, or Technical Consulting.
- Strong Linux, Kubernetes, Python, and Go skills.
- Hands-on experience with NVIDIA/AMD GPU infrastructure and CUDA/ROCm.
- Knowledge of LLM inference, GPU optimization, RDMA/InfiniBand/RoCE.
- Experience with Terraform/Helm and production cloud infrastructure.
- Solid customer-facing and problem-solving skills.
Preferred: Experience with production AI systems, GPU vendors/cloud platforms, and high-performance computing environments.