AI Product Engineer – Agent & Integrations

• Extend Duet's agent harness by integrating new data sources
• Design and implement MCP access to Duet functionality
• Write thin TypeScript connectors and wire them into the agent as composable tools
• Understand new data sources and determine efficient integration approaches
• Author and iterate on system prompts, tool designs, and skill definitions
• Develop the architecture linking prompts, tools, and skills
• Extend and improve the production agent loop
• Work on context management, streaming, Redis locks, billing, and user presentation
• Translate user needs into staged delivery plans that provide value in each sprint
• Collaborate with patent analysts and the development team to build customer-focused solutions

• Fluency in written and verbal English
• 3+ years professional software engineering experience
• Strong TypeScript/Node backend skills
• 12+ months building LLM agents, with an emphasis on integrating and orchestrating complex tools and data sources
• Track record of delivering outcomes efficiently
• Incremental delivery discipline: decompose work so each PR adds user value or represents a deliberate milestone
• Demonstrated prompt engineering as product work, including structured prompts, iteration from failure modes, and version control
• Experience integrating third-party APIs into an agent framework
• Excellent written and verbal communication with a focus on teamwork and collaboration

• Remote and co-working options
• Co-work location in Gracia, Barcelona