Software Engineer (Agent Platform)

About the role

Netic is an AI revenue platform supporting essential service industries across North America. Backed by $43M in funding from investors including Founders Fund, Greylock, Hanabi, and Dylan Field, we are scaling our team to integrate frontier AI into the physical economy. You will own the design and execution of the core systems that enable autonomous software agents to operate reliably in production settings. This role requires you to translate high-level business goals into robust technical implementations that directly impact revenue-generating workflows. You will work closely with product, research, and operations teams to ensure that the agent platform evolves in line with real-world demands. Your contributions will define the reliability and scalability standards for multi-agent orchestration in critical service environments. You will be responsible for ensuring that the platform not only functions but also adapts to the shifting needs of enterprise customers. This position places you at the intersection of AI innovation and industrial application, where your code will power tangible economic outcomes.

Key facts

What you'll do

• Architect and maintain the orchestration layer that manages, routes, and monitors multi-agent workflows within live customer environments at scale.
• Engineer testing harnesses, sandboxes, and evaluation loops that allow autonomous agents to validate their own performance and correctness before production deployment.
• Enhance the Agent Manager system by implementing guardrails, rollback mechanisms, and human-in-the-loop checkpoints that ensure safe autonomous agent improvements.
• Develop full-stack features for the platform, including data modeling, API development, and front-end tooling that enables seamless interaction with agent workflows.
• Partner directly with customers to uncover reliability gaps and translate these edge cases into platform-wide safeguards that prevent future failures.
• Optimize the performance and observability of distributed agent systems, ensuring low latency and high throughput across critical service industries.
• Define and operationalize standards for agent behavior, state management, and error handling to create consistency across diverse use cases.
• Collaborate with research and product teams to prototype new agent capabilities and assess their feasibility for integration into production workflows.
• Implement monitoring and alerting systems that provide real-time insights into agent performance, enabling rapid response to anomalies.
• Contribute to the broader open source ecosystem by documenting patterns and contributing back where appropriate to advance the field.
• Lead design discussions for new platform features, balancing technical debt with the need for rapid iteration in a fast-moving market.
• Ensure that all components of the agent platform meet strict security and compliance requirements necessary for enterprise deployment.

Requirements

• You are a recent university graduate available to start between winter 2026 and summer 2027, aligning your academic timeline with our operational needs.
• You demonstrate proficiency in Python, specifically with asyncio and FastAPI, to build scalable and responsive backend services.
• You show proficiency in TypeScript, specifically with Node and React, to develop interactive and efficient user interfaces.
• You possess a strong grasp of computer science fundamentals, with a particular emphasis on distributed systems and their practical implications.
• You have a demonstrated ability to own and ship complete projects from start to finish through internships, academic work, or personal initiatives that show real-world impact.
• You are capable of navigating high levels of ambiguity in a field where standard practices are still being defined, making sound decisions with incomplete information.
• You are prepared to work on-site in San Francisco, committing to the location and schedule required for close collaboration with the team.
• You are eligible to work in the United States and meet all legal requirements for employment in the role and location.

Nice to have

• Academic, internship, or personal project experience with LLM APIs, RAG, evaluation frameworks, or agent frameworks like LangChain or MCP that can accelerate your contributions.
• A deep interest in the mechanics of multi-step agent coordination, state management, and failure recovery that drives thoughtful design decisions.

Practical notes

• We are hiring multiple engineers for this team, creating opportunities for collaboration and cross-pollination of ideas.
• Candidates who can start before winter 2026 are encouraged to apply, as earlier start dates help us meet critical project milestones.
• Netic is an equal opportunity employer, committed to building a diverse team and providing an inclusive environment for all employees.