Senior AI Inference Engineer

This role involves:

• Architecting, implementing, and optimizing end-to-end AI inference services and agentic pipelines using Python.
• Designing autonomous AI agents that can interpret, reason about, and act on video and multi-modal inputs.
• Integrating Vision Language Models (e.g., GPT-4o, Gemini Pro Vision, LLaVA) into production-grade workflows.

You will be expected to:

• Utilize LLM/agent orchestration frameworks (LangGraph, AutoGen, Semantic Kernel, etc.) to manage complex visual AI tasks.
• Deploy and operate AI services on Kubernetes or similar platforms, ensuring reliability and scalability under heavy workloads.
• Optimize workloads for modern NVIDIA GPU architectures (Ampere, Hopper, Blackwell) focusing on real-time, high-throughput media applications.

The ideal candidate should:

• Have extensive professional experience designing and shipping AI/ML systems in production, with strong Python expertise.
• Possess a proven track record of taking AI/ML models from prototype to robust, low-latency inference services.
• Have hands-on experience building agentic systems, especially with computer vision or multi-modal inputs.