LLM Engineer
Core
Develop and integrate advanced Large Language Model (LLM) capabilities and Retrieval-Augmented Generation (RAG) systems into the Ultralytics HUB platform and ecosystem.
Role type
Senior LLM Engineer (AI/ML)
Builds
LLM-powered applications, RAG systems, and multi-modal solutions for the Ultralytics HUB platform.
Domain
Artificial Intelligence, Large Language Models, Computer Vision
Deliverable
production ML models | product features
Required skills
Python, PyTorch, LLM API integration (OpenAI, Anthropic, Gemini), RAG pipeline implementation, MongoDB, LLM fine-tuning, CI/CD automation
Preferred skills
Computer vision, object detection models (YOLO), MLOps principles
Technologies
LiteLLM, Voyage AI, GitHub Actions, MongoDB Atlas Vector Search, OpenAI API, Anthropic API, Gemini API
Responsibilities
Develop and scale LLM-powered applications using various APIs; Implement and manage multi-API workflows; Build sophisticated RAG systems with embeddings and rerankers; Design and maintain data pipelines and vector storage solutions; Fine-tune LLMs on custom datasets; Collaborate with the YOLO development team on multi-modal solutions; Automate deployment and testing processes using CI/CD pipelines.