Applied AI Engineer (Product)

Matter IntelligenceSan Francisco, CA
Onsite

About The Position

Matter is building the future of vision AI with a unique sensor and a Large World Model to create Superintelligent Vision. This system understands more than just appearance, analyzing molecular chemistry, temperature, and 3D shape from a single pixel. The team has a strong background in advanced technologies, including work for NASA/JPL and OpenAI. This role focuses on turning physics-informed models, general-purpose AI, and ultraspectral data into secure, evidence-backed intelligence products. The Product Intelligence Engineer will develop agentic workflows, integrate retrieval and tools, create reports, and design human-in-the-loop experiences to aid customers in making operational decisions.

Requirements

  • Experience building production AI applications, agent systems, workflow engines, backend services, or complex software products.
  • Strong hands-on engineering skills across APIs, stateful services, databases, asynchronous execution, testing, debugging, and production operation.
  • Practical experience with LLMs or multimodal systems, retrieval, memory, tool use, model routing, structured generation, and common failure modes.
  • Product judgment and the ability to connect technical design choices to the user decision or workflow being improved.
  • Experience building systems with security, permissions, data isolation, auditability, or human-approval requirements.

Nice To Haves

  • Experience with scientific, geospatial, industrial, defense, autonomy, or other high-consequence intelligence systems.
  • Experience building multimodal applications that combine imagery, maps, time series, documents, structured data, or sensor streams.
  • Experience with agent evaluation, constrained generation, program synthesis, durable workflow systems, or mixed cloud and edge architectures.
  • Experience working closely with product and design teams to ship customer-facing capabilities.

Responsibilities

  • Build production workflows that combine physics-informed models, LLMs, VLMs, world models, scientific code, data services, and deterministic rules through stable interfaces.
  • Design durable execution across state, planning, model routing, retrieval, memory, tool use, retries, timeouts, checkpoints, human approval, and recovery.
  • Create evidence-backed outputs that distinguish source data, model inference, system-generated synthesis, user input, and unresolved uncertainty.
  • Partner with product and design to build workflows for review, correction, comparison, approval, reporting, and recovery.
  • Build context, retrieval, memory, and indexing patterns that respect permissions, freshness, versioning, retention, and evidence lineage.
  • Evaluate real system behavior across task success, groundedness, scientific validity, safety, latency, cost, and human intervention.

Benefits

  • Competitive compensation based on experience
  • Early-stage equity package
  • 100% employer-paid health, dental, and vision coverage
  • Opportunity to work on novel sensing, data, and AI systems with real-world deployment paths to the largest industries in the world
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service