> Markdown version of [/jobs/ext/3847400-principal-software-engineer-agent-infrastructure](https://www.wearedevelopers.com/jobs/ext/3847400-principal-software-engineer-agent-infrastructure). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Principal Software Engineer, Agent Infrastructure

- **Company:** Technology Talent Network LLC
- **Location:** New York, NY, United States
- **Experience:** Expert
- **Contract:** Permanent contract
- **Skills:** Amazon Web Services, Computer Engineering, Python (Programming Language), Network Segmentation, Octopus Deploy, Open Source Technology, Backend, Kubernetes, Information Technology, Production Code, Roblox
- **Published:** October 20, 2026
- **Apply:** https://www.juju.com/job/23_B857E3662210D4488216F3C973415299

## About the Role

You Are Demonstrated experience: 8+ years building and operating backend, distributed, or infrastructure systems in production, including systems you designed that held up at scale for years.
Deep expertise in at least one of our core domains: workflow orchestration, scalable backend infrastructure, agentic runtimes, or secure sandboxing and access.
Hands-on: You spend most of your time building, and you write production code in Go, Python, Rust, or similar.
Agent-native: Agents drive your daily work.
You've experimented with swarms, loops, and orchestration, you have strong opinions on harness and model choice, and you're constantly evolving your agentic workflow.
Experienced with agents in production: You've run agents against real systems, seen how they fail, and know what the infrastructure underneath should do about it.
Bachelor's degree or equivalent experience in Computer Science, Computer Engineering, or a similar technical field., Nice to Have Security experience with systems that run untrusted code: sandbox and container isolation (gVisor, Firecracker, microVMs), Kubernetes hardening, network segmentation and egress control.
Experience working with Temporal, AWS, and self-hosted models.
Experience building and deploying production systems on Kubernetes, using GitOps and Argo CD. Contributions to open source or experience building your own product with real user traction.
For roles that are based at our headquarters in San Mateo, CA: The starting base pay for this position is as shown below.

## Description

You Will Set the technical direction: Own the design and implementation of Roblox's core agent infrastructure, and scale it to serve every internal and external customer.
Drive reliability and security: Keep long-running agents alive through deploys, restarts, and outages.
Run untrusted code in sandboxes that keep credentials out of the agent's reach and control what it can reach on the network.
Define the SLOs and observability that hold the platform to account.
Raise the bar: Keep learning and experimenting with agentic workflows, and bring what works to the team and the wider Foundation AI org.
Align across the org: Partner with Security, Engineering Efficiency, and Infrastructure so the agent platform and the systems it depends on are built in the same direction.
Multiply the team: Mentor senior engineers, lead design reviews, and push how far agents can build the agent platform itself.