Python AI Engineer (Lead/Mid/Senior)
Summary
Leads or contributes to deploying and optimizing AI systems on Kubernetes, OpenStack, and GPU clusters, using Python, Helm, and vLLM.
Role Description
- Platform & Orchestration: Deep expertise in deploying large-scale workloads on Red Hat OpenShift (Kubernetes) and OpenStack.
- Agnostic AI Deployment: Ability to independently install and optimize any AI framework or tool, including LLM orchestration, vector databases, Graph Databases, and vLLM.
- IaC & Automation: Proficiency in Helm, Ansible, Terraform, or Python to codify PoCs into production blueprints.
- Compute Optimization: Experience managing GPU acceleration (NVIDIA CUDA, MIG/slicing) and high-performance networking in containerized environments.
- Prototyping: Ability to independently deliver functional, secured PoCs from minimal documentation within days.
- Architecture & Integration: Skilled in connecting AI tools via APIs, managing authentication (OAuth/OIDC), and persistent storage.
Qualifications
- Team Lead (1), Senior (1), Mid-Level (2)
Requirements
- Start Date: ASAP
- Duration: 6-12 months
- Location: US
- Number of Positions: 4 (2 focused on Python/AI and 2 on Operations)