Applied AI Engineer - Internal

Matter Intelligence • San Francisco, CA

3d • Onsite

About The Position

Matter Intelligence is building the future of vision AI, combining a novel sensor with a Large World Model to create Superintelligent Vision. This system understands physical world data beyond visual appearance. The team has a strong track record in AI and sensor technology, having contributed to projects for NASA/JPL, OpenAI, and the U.S. Defense Department. This role is at the intersection of hardware, AI, and Earth observation, bridging Engineering and Operations. As the first hire in this role, you will collaborate with various Matter teams (sensor engineers, ML researchers, satellite systems designers, sales, leadership) to understand their workflows, identify opportunities for intelligent agents to improve efficiency, and build these agents. You will own problems end-to-end, from discovery to deployment and iteration. This is a role for an autonomous developer with strong CS fundamentals who can build production-grade agents that are depended upon.

Requirements

• B.S. in Computer Science or equivalent practical experience.
• Demonstrated ability to build and ship production software: clean code, version control, testing, CI/CD.
• Hands-on experience building with LLM APIs and/or agent frameworks — you've built something real, not just followed a tutorial.
• Strong product instincts: you can sit with a stakeholder, understand their workflow, identify what actually matters, and scope something achievable.
• Security-conscious by default: you think about access control, data handling, and failure modes before they become problems.
• Clear written and verbal communicator — you can write documentation a non-engineer will actually read.
• U.S. citizen or national, lawful permanent resident (green card holder), or eligible to obtain required authorizations from the U.S. Department of State (for ITAR compliance).

Nice To Haves

• Experience building internal tools or automation for operational teams (BizOps, RevOps, FinanceOps, etc.).
• Familiarity with agentic design patterns: tool use, memory, multi-agent coordination, human-in-the-loop flows.
• Experience with agent evaluation and observability tooling (LangSmith, Langfuse, Braintrust, or similar).
• Comfort with RAG architectures and vector database selection.
• Prior experience in a startup environment where you had to own end-to-end delivery without heavy infrastructure.

Responsibilities

• Design, build, test, and maintain production-grade AI agents and tools using current frameworks and APIs.
• Architect agentic systems that are reliable, secure, observable, and maintainable.
• Build AI-native UX patterns that reduce friction to adoption: human-in-the-loop checkpoints, auditability, graceful failure/rollback, and feedback mechanisms.
• Select and integrate appropriate tools, memory systems, and retrieval strategies for each agent's use case.
• Write clean, well-documented, version-controlled code.
• Interview stakeholders across engineering, hardware, science, sales, and leadership to identify high-leverage opportunities for automation and value creation.
• Run user interviews, workflow audits, and surveys to understand actual bottlenecks before writing a line of code.
• Translate qualitative findings into clear, scoped requirements and build plans.
• Maintain a prioritized backlog of agent opportunities with transparent reasoning on what gets built next and why.
• Work across every part of Matter; no two weeks will look the same.
• Be responsive, communicate clearly, and follow through - your coworkers are your clients.
• Own rollout and change management for what you build: onboarding, adoption, feedback loops, and iteration based on real usage.
• Share and document best practices for working with AI tools across the organization.
• Lead training session on the best practices for AI adoption and use.
• Build with security first: apply proper secret management, access control, and prompt injection defenses from day one.
• Write agent documentation that humans can actually use—runbooks, decision logs, API specs.
• Establish evaluation frameworks and monitoring so stakeholders know when an agent is working and when it isn't.
• Own quality end-to-end: you ship it, you support it, you improve it.

Benefits

• Competitive total package based on experience.
• Early-stage equity package.
• 100% employer-paid health, dental, and vision coverage.
• Unique exposure across hardware, software, science, and commercial teams.
• A front-row seat to building the world's most capable sensing and intelligence platform.

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level