Deskripsi Pekerjaan
Apex Neural Labs is seeking a high-caliber Senior AI Platform Engineer to architect, scale, and optimize our distributed inference and training infrastructure in San Francisco, CA.
In this role, you will bridge the gap between bleeding-edge machine learning models and high-throughput production infrastructure. You will design fault-tolerant systems handling millions of requests per second, optimize GPU utilization, and automate resilient continuous training pipelines.
We provide competitive equity, comprehensive health benefits, 401(k) matching, and an environment driven by engineering excellence.
Tanggung Jawab
- Architect and maintain distributed machine learning inference platforms across multi-node GPU clusters.
- Optimize model serving latency and inference costs using TensorRT, vLLM, and custom Triton inference kernels.
- Implement scalable data pipelines and feature stores supporting continuous real-time model evaluation.
- Collaborate with ML research teams to package, containerize, and deploy foundation models to production.
- Establish monitoring, observability, and automated alerting systems for drift detection and model performance.
- Maintain high infrastructure reliability, targeting 99.99% availability for critical ML inference endpoints.
Kualifikasi
- 5+ years of software engineering experience focusing on distributed systems and platform reliability.
- 3+ years of hands-on experience deploying and scaling ML models in production environments.
- Proficiency in Go, Python, and modern container orchestration platforms including Kubernetes.
- In-depth expertise with cloud infrastructure (AWS or GCP) and specialized hardware accelerators (NVIDIA GPUs).
- Deep understanding of model serving engines such as Triton Inference Server, vLLM, or TGI.
- Bachelor's or Master's degree in Computer Science, Software Engineering, or equivalent practical experience.