Responsibilities
- Design and implement platform systems supporting AI applications, intelligent agents, and retrieval-augmented generation (RAG) workflows
- Create maintainable, upgradable, and modular infrastructure architectures
- Ensure platform services are built with high availability and disaster recovery capabilities
- Collaborate with security specialists to implement compliant and controlled AI infrastructure
- Develop automated deployment pipelines to accelerate service delivery for internal teams
- Enable developer self-service through standardized deployment methods and tools
- Maintain reusable templates and integration patterns for generative AI, agents, RAG, and agent-to-agent systems
- Implement monitoring solutions for AI system performance, usage, cost, and operational health
- Stay current with advancements in AI by evaluating new frameworks, tools, and research
- Lead research and development efforts to evolve platform capabilities in line with emerging agentic and LLM technologies
