Senior/Director Product Manager (Claude LLM Integration & MCP Platform)

What you'll do

• Define MCP server product strategy including tool taxonomy, inputs/outputs, and natural language discoverability
• Prioritize tool development for internal and external use cases
• Own product roadmap from v1 through GA including feature gates, versioning, and deprecation policy
• Design, document, and validate LLM-powered client use cases querying Pixalate's data via MCP
• Write structured tool descriptions and parameter schemas optimized for LLM context
• Partner with research and data science to prototype agentic workflows and evaluate output quality
• Write concise PRDs with clear problem statements, requirements, input/output contracts, and non-goals
• Champion small, shippable iterations over large releases
• Define and maintain API contracts including versioning, deprecation, and schema change protocols
• Run structured QA on tool outputs to ensure LLM-friendly, consistent responses
• Own product model for external auth (OAuth 2.0 or API key) and capability-scoped access
• Collaborate with security and engineering to ensure compliance and data governance
• Own developer-facing documentation and onboarding flows for external clients
• Gather and prioritize feedback from early adopters
• Work fluidly across US, EU, and APAC time zones with async-first communication
• Adapt availability around key global milestones

Requirements

• B.S. or B.A. in Computer Science, Computer Engineering, or a closely related technical discipline
• 5+ years of product management experience, with at least 2–3 years owning developer tools, data APIs, AI/ML platforms, or LLM-adjacent products
• Availability and willingness to work across global time zones — US, EU, and APAC — with flexibility to accommodate distributed teams and international clients
• Deep, hands-on API experience — owned API products end-to-end: endpoint design, versioning, auth flows, rate limiting, developer documentation, and client onboarding
• Hands-on, proven experience working with LLMs — building products on top of them, evaluating model outputs, designing prompt and tool architectures (Claude, GPT-4, Gemini, or equivalent)
• Direct experience with MCP: set up, connected, or built an MCP server or client, understanding tools, resources, and prompts in the protocol
• Demonstrated outside-in product development — decisions shaped by client interviews, API usage data, developer feedback, or real usage patterns
• Experience designing tool or function definitions for LLM consumption — understanding model context, tool descriptions, and parameter schemas
• Track record of delivering data or developer products through fast, iterative releases

Tech stack

Benefits