Contractor Infrastructure Engineer - Software Engineer

• 4–7 years experience in systems software or infrastructure engineering, preferably with exposure to AI/ML workloads.
• Deep expertise in CUDA, NCCL, ROCm, or other accelerator programming frameworks.
• Familiarity with LLM inference runtimes (TensorRT-LLM, vLLM, ONNXRuntime).
• Experience with Kubernetes scheduling, device plugin development, and runtime patching for heterogeneous compute.
• Strong Python/C++ and Linux systems programming skills.
• Passion for building scalable, portable, and secure AI infrastructure.

• Design and implement cross-platform hardware detection systems for GPUs/TPUs/NPUs using CUDA, ROCm, and low-level runtime interfaces.
• Build and maintain plugin-based infrastructure for capability scoring, power efficiency tuning, and memory optimization.
• Develop hardware abstraction layers (HAL) and performance benchmarking tools to optimize AI agents for cloud-native inference.
• Extend container-based MLOps systems (Docker/Kubernetes) with support for hardware-specific runtime containers (e.g., TensorRT, vLLM, ROCm).
• Automate driver validation, container security hardening, and runtime health monitoring across deployments.
• Integrate telemetry systems (Prometheus, Grafana) to surface per-device inference performance metrics and health status.
• Collaborate with solutions and DevOps teams to ensure hardware-aware agent deployment across cloud providers.

What is the last date for applying to the job?

Which countries are accepted for this remote job?