Tech Stack

Description

You will design, implement, and optimize end-to-end AI inference services and agentic pipelines for major media and sports organizations. You'll own the full lifecycle from discovery and architecture to deployment on GPU and cloud infrastructure, transforming ambiguous business problems into scalable, high-performance AI architectures.

Requirements

• Significant professional experience building and shipping AI/ML systems in production with strong Python
• Proven track record of taking models from prototypes into robust, low-latency inference services
• Extensive hands-on experience building agentic systems involving computer vision or multi-modal inputs
• Practical experience integrating Vision Language Models and LLM/agent orchestration frameworks (LangGraph, AutoGen, Semantic Kernel)
• Strong practical experience with Kubernetes in production and distributed systems on AWS

Responsibilities

• Architect, implement, and optimize end-to-end AI inference services and agentic pipelines in Python
• Design autonomous agents for interpreting, reasoning, and acting on video and multi-modal content
• Integrate Vision Language Models (GPT-4o, Gemini Pro Vision, LLaVA) into production workflows
• Deploy and operate services on Kubernetes ensuring scalability under heavy media workloads
• Collaborate with clients in pre-sales discussions to shape solutions and validate feasibility