Agent Infrastructure (IC)
Matter Intelligence4 hours ago
Responsibilities
- Build and operate a production agent runtime integrating physics-informed models, LLMs, VLMs, world models, scientific code, data services, and deterministic business rules.
- Design durable execution with state, planning, tool selection, retries, timeouts, cancellation, checkpoints, provenance, human approval, and recovery.
- Build retrieval, RAG, memory, and indexing systems that address tenancy, permissions, freshness, versioning, retention, and evidence lineage.
- Create evidence-first outputs that distinguish source data, model inference, system synthesis, user input, and unresolved uncertainty.
- Integrate continuous evaluation for task success, groundedness, scientific validity, safety, latency, cost, and human intervention.
- Partner with product, design, AI platform, Signal and Evaluation, and Telemetry teams to create reusable APIs, tools, and human-in-the-loop workflows.
Requirements
- Experience building production agent infrastructure, applied-AI platforms, workflow engines, distributed systems, or complex AI products.
- Strong hands-on software engineering skills in architecture, APIs, stateful services, databases, asynchronous execution, testing, debugging, and production operations.
- Practical experience with LLMs, VLMs, multimodal systems, RAG, memory, tool use, model routing, structured generation, and agent failure modes.
- Experience building systems with security, permissions, data isolation, auditability, and human approval requirements.
- Sound product judgment and ability to explain uncertain system behavior to technical and non-technical teams.
- Preferred: experience with scientific, geospatial, industrial, defense, autonomy, or other high-consequence customer-intelligence systems.
- Preferred: experience building multimodal applications combining imagery, time series, maps, documents, structured data, or sensor streams.
- Preferred: experience with agent evaluation, reinforcement learning or world-model environments, model routing, constrained decoding, or durable workflow systems.
- Preferred: familiarity with edge or intermittently connected operation, local model execution, or mixed cloud and edge architectures.
- Applicants must be U.S. citizens or nationals, lawful permanent residents, or eligible to obtain required U.S. Department of State authorizations under ITAR requirements.
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.
- Onsite work required in San Francisco, California.
Categories
About Matter Intelligence
Matter specializes in advancing sensors and geospatial AI that capture "extreme-resolution" images of natural and artificial materials from space to surface, creating never-seen data of all matter globally. Our sensors simultaneously measure shape, composition, and temperature to understand and predict real-world events like never before. Matter's data accelerates computer vision and contextual geospatial modeling to unlock the next generation of intelligence.