Deskripsi Pekerjaan
Apex Neural Systems is building next-generation distributed inference infrastructure. We are seeking an exceptional Senior AI Platform Engineer to design, scale, and optimize low-latency deployment pipelines for enterprise-grade foundation models.
In this role, you will bridge the gap between production machine learning models and high-throughput systems infrastructure, driving mission-critical reliability across our hybrid GPU compute clusters.
Tanggung Jawab
- Architect and maintain low-latency inference runtimes for LLMs and multi-modal models.
- Design resilient distributed systems on multi-node GPU/TPU clusters using Kubernetes.
- Build automated monitoring and orchestration pipelines for high-throughput model serving.
- Optimize compute efficiency, memory bandwidth, and GPU kernel operations across platforms.
- Establish CI/CD deployment standards for model artifact staging and zero-downtime rollouts.
- Collaborate with ML research teams to translate experimental architectures into production services.
Kualifikasi
- 5+ years of production experience building and scaling distributed backend systems.
- Strong proficiency in Python and Go, alongside systems-level performance tuning.
- Extensive hands-on experience orchestrating workloads using Kubernetes and Docker.
- Practical exposure to inference engines such as TensorRT-LLM, vLLM, or Triton.
- Demonstrated knowledge of modern cloud infrastructure (AWS or GCP) and IaC tooling (Terraform).
- Bachelor's or Master's degree in Computer Science, or equivalent practical experience.