Responsibilities
- Design and improve AI and machine learning applications across diverse projects
- Build and refine Large Language Model (LLM) and Retrieval-Augmented Generation (RAG) systems using LangChain frameworks
- Support the architecture and implementation of scalable, production-ready AI platforms grounded in modern software engineering standards
- Create and train computer vision models using PyTorch
- Develop reliable and efficient software solutions in Python, adhering to industry best practices
- Configure and maintain containerized environments using Docker and Docker Compose
- Manage source code through Git and ensure consistent deployments via CI/CD pipelines
- Work with cross-functional teams to embed AI and LLM capabilities into current platforms
