Applied AI Engineer - Internal

About the role

Matter is building technology at the intersection of hardware, AI, and Earth observation. This role sits at the boundary of Engineering and Operations. As the first hire in this role, you'll work directly with teams across Matter: sensor engineers, ML researchers, satellite systems designers, sales, and leadership. Your job is to understand how they work, identify where intelligent agents can compress hours into seconds, and build them. You might spend a week designing a multi-agent workflow to automate competitive intelligence tracking, then shift to an internal tool that gives the hardware team instant retrieval across five documentation systems. You own problems end-to-end - from discovery through deployment through iteration. This isn't a role for someone who wants to follow a ticket queue. It's for a developer with strong CS fundamentals who can operate with autonomy, earn trust across a demanding organization, and ship production-grade agents that people actually depend on.

Responsibilities

• Agent Development & Engineering
• 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. You set the standard.
• Product Discovery & Requirements
• 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.
• Cross-Functional Partnership
• Work across every part of Matter; no two weeks will look the same. One week you're building a pipeline tool for the payload team; the next you're automating how sales tracks relationships.
• 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.
• Quality, Security & Documentation
• 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.
• The Tooling Landscape You Should Know
• AI agent development moves fast. We expect fluency across the current stack (examples, constantly changing):
• Agent frameworks & orchestration: Anthropic SDK / Claude API, MCP, Skills, orchestration tools
• Workflow/process automation: n8n, Zapier/Make, Retool workflows, Airtable automations (or equivalents)
• AI-native development: Claude Code, Codex, Cursor, GitHub Copilot
• Observability & evaluation: LangSmith, Langfuse, Braintrust, DeepEval (or equivalents) - you instrument what you build and measure whether it works
• Data & memory: Vector databases (Pinecone, Chroma, Weaviate, pg-vector), RAG pipeline design, structured vs. unstructured retrieval tradeoffs
• Security: Secret management (AWS Secrets Manager, HashiCorp Vault), OAuth 2.0, RBAC, least-privilege design, prompt injection defense
• Documentation & API design: Structured logging, clear runbooks - because agents that nobody understands get turned off

Requirements

• Required
• 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-o

Benefits

Additional Information

About Matter Intelligence Matter Intelligence is building the future of vision AI: pairing a world-first sensor that sees molecular chemistry, temperature, and 3D shape with a Large World Model-the most powerful intelligence engine for the physical world. This system doesn't just see what something looks like; it understands everything from a single pixel. We call this Superintelligent Vision. Our team has delivered technologies to Mars for NASA/JPL, co-founded and led infrastructure for OpenAI, designed cutting-edge sensors for U.S. Defense, and invented core algorithms for spectral and 3D imaging. We've come together to build the next infrastructure for vision and intelligence in the physical world.

Your Match

How well this role fits your profile.

Company Intel

What employees say

Worked at matter-intelligence? Share your experience