You will work at the intersection of AI, search infrastructure, and developer experience to make enterprise knowledge instantly accessible, actionable, and AI-ready.
How will you make an impact?
- Integrate CMS with AWS Knowledge Hub to allow seamless RAG-based search across diverse data types—eliminating the need to copy data into Knowledge Hub instances.
- Extend Knowledge Hub capabilities to ingest and index non-knowledge assets, including structured data, documents, tickets, logs, and other enterprise sources.
- Build secure, scalable connectors to read directly from customer-maintained indices and data repositories.
- Enable self-service capabilities for customers to manage content sources using App Flow, Tray.ai, configure ingestion rules, and set up search parameters independently.
- Collaborate with the NLP/AI team to optimize relevance and performance for RAG search pipelines.
- Work closely with product and UX teams to design intuitive, powerful experiences around self-service data onboarding and search configuration.
- Implement data governance, access control, and observability features to ensure enterprise readiness.
Have you got what it takes?
- Proven experience with search infrastructure, RAG pipelines, and LLM-based applications.
- 2+ Years’ hands-on experience with AWS Knowledge Hub, AppFlow, Tray.ai, or equivalent cloud-based indexing/search platforms.
- Strong backend development skills (Python, Typescript/NodeJS, .NET/Java) and familiarity with building and consuming REST APIs.
- Infrastructure as a code (IAAS) service like AWS Cloud formation, CDK knowledge
- Deep understanding of data ingestion pipelines, index management, and search query optimization.
- Experience working with unstructured and semi-structured data in real-world enterprise settings.
- Ability to design for scale, security, and multi-tenant environment.
Tech Manager, Engineering, CX
Individual Contributor