AI Product Engineer

Samba is a media intelligence company. We know what the world is watching, reading, and thinking about — in real time, at scale, across every screen. Our data exists with the consent of over a billion people, organized into the most complete picture of consumer attention ever built. The biggest brands in the world use that picture to make smarter decisions. We think it’s the most interesting data asset on the planet, because it’s the most culturally relevant. WHAT YOU'LL DO Build and deploy AI agents using modern agent SDKs (Claude, OpenAI, or similar) with custom tools and function calling Design and build tool harnesses and execution environments for agents—both on desktop (local CLI, IDE integrations) and in the cloud (containerized, API-driven) Partner with internal teams across the organization to understand their workflows, identify automation opportunities, and build agents tailored to their use cases Think critically about LLM capabilities and limitations—understand the differences between models, when to use which, and how to get the best results from each Develop context engineering strategies—understanding how to give LLMs the right information at the right time within token limits Build and maintain custom tool libraries that agents can use to interact with internal systems, APIs, and data sources Deploy and manage agents in cloud environments with proper mo [... source excerpt omitted ...] ling, and cost controls Optimize LLM costs and performance through prompt engineering, caching, and smart model selection WHO YOU ARE You’ve built AI agents and shipped them to production—not just prototypes You’ve deployed agents in cloud environments and dealt with the real-world challenges that come with it You’ve built tools, harnesses, or scaffolding that agents use to accomplish tasks You use Claude Code and Cursor daily—you’re deeply comfortable with AI-assisted development, including headless mode, multi-file editing, and MCP server integration You think critically about LLMs—you understand how they work under the hood, not just how to call an API You understand the