Deskripsi Pekerjaan
Nexus Core AI is seeking a Senior AI Platform Engineer to build and scale the compute infrastructure powering our foundation models. You will architect distributed training systems, optimize large-scale inference runtimes, and maintain high-availability GPU infrastructure in production.
Tanggung Jawab
- Architect and maintain multi-cloud Kubernetes clusters optimized for distributed GPU training and inference workloads.
- Deploy, optimize, and scale inference serving engines using vLLM, TensorRT-LLM, and Triton.
- Automate cluster provisioning, workload orchestration, and failure recovery using Terraform and custom operators.
- Partner with ML research teams to unblock pipeline bottlenecks from prototyping through production serving.
- Establish system-wide telemetry, tracing, and GPU utilization metrics to optimize cloud spend.
- Implement security protocols and access controls across core data pipelines and model APIs.
Kualifikasi
- 5+ years of software engineering experience focusing on distributed systems, SRE, or platform engineering.
- 3+ years of production experience managing multi-node Kubernetes clusters on AWS or GCP.
- Proficiency in Go, Python, and containerized deployment tooling.
- Direct experience optimizing distributed deep learning workloads and GPU orchestration.
- Strong background in network performance tuning, specifically RDMA, InfiniBand, or VPC peering.
- BS or MS in Computer Science, Computer Engineering, or equivalent practical experience.