Description

You will build and deploy AI systems end-to-end, focusing on inference and deployment pipelines.

Responsibilities

• Develop and optimize AI inference applications using PyTorch and TensorFlow.
• Implement and manage CI/CD deployment pipelines involving Nvidia Dynamo, Nvidia NIM, vLLM, and Ollama.
• Manage AI development environments using tools like Google Colab and Jupyter Notebooks.
• Stream data between cloud and data center environments using protocols like IRC, reverse NAT, WebRTC, and RTSP.
• Analyze and address performance bottlenecks in AI model inference runs.

Required Skills

• 8+ years of professional experience in software engineering or AI development.
• Expertise in deep learning frameworks, specifically PyTorch and TensorFlow.
• Hands-on experience with CI/CD practices for ML model deployment.
• Strong understanding of inference frameworks, including vLLM and SGLang.
• Proficiency in scaling both training and inference models.
• Familiarity with AI tooling for UI generation (e.g., Workik, Builder.io).
• Knowledge of data streaming protocols (IRC, WebRTC, RTSP).

Key Skills

Education

Any Graduate