AI Enablement Engineer

       Context Engineering & Retrieval:

·       Build “context packers” that assemble repo, doc, and ticket context for AI tools, with latency under 200 ms.

·       Design and implement semantic/code search, RAG, and repo‑level indexing for large monorepos and service boundaries.

·       Implement context-ranking logic (by file relevance, recency, dependencies) instead of dumping entire repos into prompts.

·       Integrate with MCP-style protocols or internal APIs so AI tools can access internal code, APIs, tickets, and schemas.

·       Prompt Engineering & Orchestration:

·       Create and maintain a library of reusable prompts for common tasks:

·       Code generation, refactoring, test creation, inline documentation, debugging, migration.

·       Implement versioning, tagging, A/B testing, and quality scoring for prompts.

·       Collaborate with brownfield teams to codify patterns for legacy systems and migration.

·       Help build guardrails (e.g., safety, style, security) around generated outputs.

·       Tooling, Integrations, and Observability:

·       Extend IDEs (VS Code, JetBrains, Cursor, etc.) with internal AI plugins, status bars, and context-aware assistants.

·       Build AI-powered CI/CD workflows, e.g., PR auto-remediation, test generation, and risk/impact summaries.

·       Add telemetry to track usage, latency, failure rates, token consumption, and quality of AI-generated code.

·       Monitor and tune model performance, prompt effectiveness, and guardrail coverage.

·       Collaboration with Engineering Teams:

·       Partner with product teams to identify high-friction workflows where AI can make the biggest difference.

·       Conduct onboarding sessions, walkthroughs, and “debugging with AI” sessions with developers.

·       Collect feedback and iterate on the platform to make it more usable for brownfield codebases.