• Design and build LLM-powered features and AI agent pipelines — from prompt to production • Extend and optimize our RAG / knowledge base system: chunking strategies, embedding models, vector search, hybrid retrieval (BM25 + semantic), and reranking • Implement agentic workflows with tool use, multi-step reasoning and structured outputs • Build document- and email-processing pipelines that leverage LLMs for classification, extraction and summarization • Integrate and manage LLM providers (OpenAI, Anthropic, etc.) and AI SDKs across the stack • Design evaluation frameworks and feedback loops to measure and continuously improve AI output quality • Build and optimize agents for our growing template library • Operate in an AI-first development setup powered by Claude/Cursor

• Lead AI initiatives across the organization • Own and drive implementation of AI-powered solutions • Ensure AI capabilities are integrated into existing systems and practices • Mentor developers and uplift engineering team skills in AI • Research and stay updated with AI technologies and recommend improvements • Establish AI development standards and ensure compliance with best practices • Collaborate with teams to align AI initiatives with business priorities

• Design and build internal AI tooling that supports automated remediation and migration workflows across the developer platform • Deploy and integrate AI tools (including LLM-based assistants, code analysis agents, and CI/CD-integrated tooling) into existing developer workflows • Troubleshoot and support developers experiencing issues with AI tooling — acting as the subject matter expert for AI-assisted development • Collaborate with teams to embed AI capabilities into build practices, upgrade cycles and security patching pipelines • Measure and report on outcomes: faster upgrade cycles, reduced manual remediation effort, and cost avoidance • Continuously improve tooling based on developer feedback and usage patterns

• Design, develop, and optimize applications leveraging internal LLM platforms • Create, test, and maintain high-quality prompts to drive accurate and predictable outputs • Apply advanced prompting techniques including: Few-shot prompting, Prompt chaining, RAG (Retrieval-Augmented Generation) • Build full-stack, end-to-end GenAI applications • Design and implement backend services integrating LLMs with enterprise systems • Develop or collaborate on web-based user interfaces • Integrate GenAI capabilities into existing applications and workflows • Analyze structured and unstructured data for GenAI use cases • Translate business requirements into LLM-driven workflows • Document design decisions, prompts, and system behavior clearly