AI Infrastructure Engineer

Role Overview

Build and optimize the AI infrastructure that powers Pokee’s RL-trained AI agents—from scalable training pipelines to high-performance inference serving. You’ll help ensure research results translate into production-grade systems that enterprises can trust across cloud and on-device deployments.

Responsibilities

• Design, build, and maintain scalable training and inference infrastructure for RL-based agent models
• Optimize model serving for latency, throughput, and cost across cloud (AWS, GCP) and on-prem/on-device
• Develop and manage CI/CD, experiment tracking, and model versioning systems
• Implement efficient data pipelines for training data collection, preprocessing, and reward signal computation
• Collaborate with research scientists to productionize new algorithms and model architectures
• Ensure infrastructure meets enterprise reliability, security, and compliance requirements (e.g., SOC 2, data residency)

Requirements

• 3+ years of experience in ML infrastructure / ML platform engineering / related systems roles
• Strong proficiency in Python and systems-level languages: Rust, C++, or Go
• Hands-on experience with ML serving frameworks: vLLM, TensorRT, Triton, ONNX Runtime, or similar
• Experience with container orchestration (Kubernetes, Docker) and cloud infrastructure (AWS or GCP)
• Solid understanding of GPU computing, distributed systems, and performance profiling
• Familiarity with ML experiment tracking and orchestration tools: MLflow, Weights & Biases, Airflow, or similar

Bonus Points

• On-device/edge inference optimization (e.g., GGUF quantization, TensorRT-LLM, CoreML, QNN)
• On-prem GPU deployments (e.g., NVIDIA DGX, Dell PowerEdge, Lenovo ThinkStation)
• Experience supporting RL training loops or online learning systems in production
• Background in enterprise software with security/compliance frameworks
• Contributions to open-source ML infrastructure