Responsibilities
- Architecting, constructing, and deploying artificial intelligence and generative AI systems, such as applications powered by large language models, conversational agents, and smart software solutions
- Creating and refining strategies for prompt engineering, including performance assessment and iterative improvements
- Developing retrieval-augmented generation (RAG) pipelines leveraging vector database technologies
- Integrating large language models and other AI models into cloud-hosted applications and application programming interfaces
- Designing and implementing workflows based on autonomous agents and automated AI processes
- Continuously investigating, assessing, and adopting emerging AI tools, models, and frameworks
