AI Infrastructure Engineer

Role responsibilities

As an AI Infrastructure Engineer, you will design, build, and maintain scalable training and inference infrastructure for RL-based AI agent models. You will also optimize model serving for latency, throughput, and cost across various environments.

Requirements

The role requires 3+ years of experience in ML infrastructure or a related systems role, with strong proficiency in Python and systems-level languages. Familiarity with ML serving frameworks and cloud infrastructure is also essential.

Key skills

Machine Learning Infrastructure, ML Platform Engineering, Python, Rust, C++, Go, ML Serving Frameworks, Container Orchestration, Kubernetes, Docker, Cloud Infrastructure, AWS, GCP, GPU Computing, Distributed Systems, Data Pipelines

Keywords

AI Infrastructure Engineer, Reinforcement Learning, Training Pipelines, Inference Serving, CI/CD Pipelines, Experiment Tracking, Model Versioning, Data Preprocessing, Reward Signal Computation, Enterprise Requirements, Reliability, Security, Compliance, SOC 2, Data Residency, On-Device Deployments, Edge Inference Optimization, Open-Source ML Infrastructure