Deskripsi Pekerjaan
Nexus Systems is seeking an experienced Senior AI Infrastructure Engineer to design, deploy, and scale high-throughput training and inference platforms. You will work directly on multi-node GPU clusters, optimize networking pipelines, and bridge production infrastructure with cutting-edge machine learning research.
Tanggung Jawab
- Architect and manage high-availability Kubernetes clusters for distributed GPU computing.
- Design and maintain low-latency model inference pipelines handling large-scale production traffic.
- Automate training orchestration workflows using PyTorch, Ray, and custom schedulers.
- Implement telemetry, profiling, and cost-allocation tooling across multi-cloud GPU instances.
- Collaborate with ML engineers to optimize model runtime using TensorRT and vLLM.
- Establish reliable CI/CD pipelines for automated testing and deployment of ML platform services.
Kualifikasi
- 5+ years of software or platform engineering experience in production distributed systems.
- Hands-on experience deploying and scaling multi-node GPU clusters on Kubernetes.
- Proficiency in Python, Go, and core Linux system internals.
- Practical knowledge of inference engines such as vLLM, Triton, or TensorRT-LLM.
- Strong background in distributed networking fundamentals, including RDMA, InfiniBand, or RoCE.
- BS or MS in Computer Science, Computer Engineering, or equivalent practical experience.