AI Product Engineer

Samba; San Francisco (CA); Hybrid; USD 150,000 - 230,000; Full time

Job summary

Samba is seeking a skilled AI engineer to build production-ready agents using Claude, OpenAI, and internal toolkits. You will design tool harnesses, run agents in cloud environments, and optimize costs while ensuring robust observability and reliability.

You will collaborate with cross-functional teams, reason about model choices (Claude, GPT, Gemini, open-source), and ship practical solutions quickly with strong engineering discipline.

Qualifications

• Experience building AI agents deployed to production.
• Experience with cloud deployments and real-world challenges.
• Familiarity with MCP servers and tool libraries for agents.
• Open-source contributions to AI/ML projects.
• Observability and monitoring for LLM applications.

Responsibilities

• Build and deploy AI agents using modern SDKs with custom tools and function calling.
• Design and build tool harnesses and execution environments for agents in desktop and cloud.
• Collaborate with internal teams to understand workflows and automation opportunities.
• Critically evaluate LLM capabilities and model selection for tasks.
• Develop context engineering strategies for effective LLM prompts.
• Maintain custom tool libraries for internal APIs and data sources.
• Deploy and manage agents in cloud environments with monitoring and cost controls.
• Optimize LLM costs and performance via prompt engineering and caching.

Skills

AI agent development

Production deployment

Cloud environments

ToolHarness design

LLM debugging

Observability for LLM

Cross-functional collaboration

Multi-agent systems

MCP server experience

Open-source contributions

Tools

Claude

OpenAI API

Cursor

GCP

AWS

Azure

Containerization

Model Context Protocol

Job description

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 monitoring, error handling, 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 differences between models (Claude, GPT, Gemini, open-source) and can reason about which to use for a given task

• You have strong product sense—you focus on what users actually need, not just what’s technically interesting

• You're pragmatic—you ship 80% solutions quickly and iterate based on feedback

• You can sit with a non-technical team, understand their pain points, and translate that into an agent that actually helps

• You take ownership and drive things from idea to measurable impact

• You communicate clearly—you can explain complex AI systems to anyone in the company

• You stay current with the rapidly evolving AI landscape and bring new ideas to the team

• You're comfortable working across cloud platforms (GCP, AWS, Azure) and containerized environments

• Experience with advanced agent patterns or multi-agent systems

• Experience building and configuring MCP (Model Context Protocol) servers

• Open-source contributions to AI/ML projects

• Familiarity with observability tools for LLM applications

• Media, ad tech, or streaming data domain knowledge

Samba may collect personal information directly from you, as a job applicant, Samba may also receive personal information from third parties, for example, in connection with a background, employment or reference check, in accordance with the applicable law.

Samba is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. We strive to empower connection with one another, reflect the communities we serve, and tackle meaningful projects that make a real impact.

For further details, please see Samba's Applicant Privacy Policy.

For residents of the EU , Samba Inc. is the data controller.