Key Responsibilities
- Design, build, and optimize AI-powered applications leveraging generative models and large language models (LLMs)
- Develop Retrieval-Augmented Generation (RAG) pipelines and scalable AI services for production deployment
- Collaborate with cross-functional teams to integrate intelligent capabilities into software products
- Perform prompt engineering, model integration, and performance optimization of AI systems
- Monitor, evaluate, and maintain AI systems in production, including testing and documentation
- Provide feedback on code and prompt implementations based on engineering and responsible AI best practices
Requirements
- 3-5 years of relevant experience in machine learning, generative AI, or related fields
- Proficiency in Python and experience with LLMs or generative models
- Strong understanding of prompt engineering, RAG pipelines, and AI service deployment
- Ability to work independently and collaborate with teams of varying skill levels
- Experience with AI system evaluation, optimization, and production monitoring