- Company Name
- fanvue
- Job Title
- AI Engineer
- Job Description
-
**Job Title:** AI Engineer – Developer Tooling
**Role Summary:**
Lead the design, implementation, and governance of AI‑assisted development tools across the engineering organization. Define the AI coding stack, build supporting infrastructure, and create processes that boost developer velocity, code quality, and security while ensuring responsible and safe AI usage.
**Expectations:**
- Own end‑to‑end delivery of AI‑powered tooling and workflows.
- Drive adoption of standardized AI coding practices across IDEs, PR processes, and CI/CD pipelines.
- Deliver measurable improvements in developer productivity (e.g., PR cycle time, throughput).
- Continuously evaluate emerging AI developer solutions and make go/no‑go decisions.
- Operate autonomously, experiment rapidly, and resolve ambiguous technical problems.
**Key Responsibilities:**
- Align the codebase with modern AI coding assistants (e.g., Cursor, Claude Code).
- Define, document, and roll out the AI‑assisted development stack for all engineers.
- Build and maintain MCP servers and AI‑ready infrastructure (Context 7, Puppeteer, MCP Compass).
- Enable parallelized development workflows with confidence in AI‑generated code.
- Establish best‑practice guidelines for AI‑assisted coding, reviews, and refactoring.
- Create training materials, playbooks, and documentation to promote safe AI usage.
- Track, analyze, and report key productivity metrics (PR cycle time, code quality scores).
- Conduct regular assessments of new AI tools/vendors and implement kill‑switches as needed.
**Required Skills:**
- Strong production software engineering experience with TypeScript.
- Hands‑on expertise with AI coding tools (Cursor, Claude Code) and familiarity with Aider, Cline, CodeRabbit, GitHub Copilot.
- Experience operating MCP servers and related tooling (Context 7, Puppeteer, MCP Compass).
- Ability to create, manage, and deploy AI agent skills in real‑world codebases.
- Solid understanding of LLM fundamentals: RAG pipelines, embeddings, tokenization, fine‑tuning, performance trade‑offs.
- Proficiency with GitHub workflows, CI/CD pipelines, and secure coding practices.
- Demonstrated impact on engineering productivity through AI integration.
- Highly autonomous, experimental mindset; comfortable making safety and quality trade‑off decisions.
**Required Education & Certifications:**
- Bachelor’s degree in Computer Science, Software Engineering, or a related field (or equivalent practical experience).
- Optional: certifications in Machine Learning, AI/ML, or Cloud Infrastructure (e.g., AWS, Azure) are a plus.