Sr. AI Engineer

As an AI Interfaces Engineer, you will design and build agent‑mediated interfaces across our product and our internal tooling. You will help establish a new pattern of AI‑native frontend development, where prototypes evolve against real platform data over MCP and move efficiently from concept to deployable experience. Your focus areas will include AI chat interfaces, agentic use cases, and product‑facing MCP servers.

This is a primarily hands‑on role that blends prompt engineering, full‑stack engineering, and AI‑native product thinking within a fast‑paced startup environment.

• Partner with product management, design, and engineering to build a prototype‑to‑production pipeline where teams iterate on agent‑mediated experiences against real platform data over MCP, shortening the path from design to deployable code.
• Design and build AI chat interfaces and agentic experiences, bringing natural language and agent‑mediated workflows directly to the customer surfaces.
• Design and build product‑facing MCP servers and agent tooling, platform data, documentation, and workflow state to customer‑facing agents and internal flows alike.
• Design and build agent‑mediated interfaces for internal tooling, including configuration tools and admin workflows, demonstrating the value of these patterns before they extend to external product surfaces.
• Define and operate the prompt engineering practice: writing, versioning, and evaluating prompts, tool specifications, and agent behaviors with reproducible harnesses and clear quality metrics.
• Establish evaluation methodology for agent‑mediated UX, including user‑task success rates, latency budgets, guardrail compliance, and iterative improvement cycles tied to real user sessions.
• Drive adoption of agent‑mediated interface patterns, partnering with frontend, backend, product, and platform teams to ensure these approaches are first‑class in the product architecture rather than bolt‑ons.
• Take full ownership of initiatives, from early concept discovery and prototype through production deployment, telemetry, and ongoing iteration.

• Demonstrated experience shipping production applications built around LLMs and agent frameworks, including tool use, multi‑turn context management, and safe handling of non‑deterministic model output.
• Strong product and UX sensibility: ability to translate ambiguous workflows into clear interaction designs and to advocate effectively for user needs in cross‑functional discussions.
• Fluency in prompt engineering, including multi‑turn conversation design, tool definition, context‑window management, and systematic evaluation of agent behavior.
• Full‑stack engineering ability, with strong frontend depth in Type Script and React and the ability to move into Python backends, build REST/Web Socket services, and wire interfaces to real data sources.
• Hands‑on experience with agent tool protocols (MCP or equivalent) and with designing tool surfaces that are both expressive for agents and safe at production scale.
• Experience with agent‑mediated code generation tools (Claude Code, Codex) in a production setting, including writing prompts, skills, or agents that non‑engineers use.
• Experience with cloud platforms (AWS preferred) and using modern CI/CD workflows.
• Comfort operating in ambiguity within an emerging engineering practice, partnering with other founding contributors to set direction and establish patterns across teams.

• Bachelor's degree in CS, HCI, Design, or a related field.
• Experience integrating with collaboration and knowledge systems such as Git Hub, Confluence, Jira, or Notion, including building programmatic access layers over them.
• Experience working directly with designers in Figma or comparable tooling, including translating design intent into working code and feeding design iteration from production data.
• Background in developer tooling, internal admin platforms, or configuration‑heavy products.

• Experience designing information architecture for knowledge‑dense domains, unifying structured and unstructured content (code, documents, issue trackers, wikis) into coherent representations that both humans and agents can navigate.
• Experience with retrieval, semantic search, or vector‑store backed knowledge systems at scale.
• Experience building and operating microservices in production.