AI and Data Engineer

- Design flexible agentic AI architectures that accommodate multiple model providers and deployment modes - Develop modular and reusable components for prompting, orchestration, tool execution, and evaluation to facilitate rapid AI capability development - Integrate large language models, embeddings, RAG pipelines, and memory mechanisms into production-ready systems - Utilize advanced prompting techniques and orchestration frameworks to ensure goal-directed autonomy with necessary guardrails and human oversight - Establish evaluation frameworks to assess the accuracy, safety, and business impact of AI systems - Enhance models and workflows for cost, speed, and scalability through systematic benchmarking and experimentation - Construct data pipelines for the continuous processing of structured and unstructured data for RAG systems - Employ unified processing workflows for various data modalities, including document understanding and summarization - Utilize vector databases and optimization techniques to diminish hallucinations in RAG systems - Implement safety filters, access controls, and monitoring mechanisms for secure AI system deployment - Scale and securely deploy AI services using AWS or similar cloud platforms - Utilize containerization tools like Docker or Kubernetes for flexible deployments - Apply CI/CD practices for AI systems, ensuring automated testing and safe rollout of updates - Utilize asynchronous programming patterns to support scalable workflows - Deliver optimized, portable application artifacts via modern build and packaging workflows - Employ AI assistance tools to enhance the development process while preserving code quality - Collaborate with clients to uncover high-value AI opportunities and refine solution requirements - Present technical solutions to both technical and non-technical audiences - Facilitate workshops to expedite adoption of AI technologies - Provide guidance on ethical AI practices and compliance regulations