> Markdown version of [/jobs/ext/4556128-staff-platform-reliability-engineer-agentic-ai-san-francisco](https://www.wearedevelopers.com/jobs/ext/4556128-staff-platform-reliability-engineer-agentic-ai-san-francisco). 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).

---

# Staff Platform & Reliability Engineer - Agentic AI (San Francisco)

- **Company:** Syndesus, Inc.
- **Location:** San Francisco, CA, United States
- **Experience:** Expert
- **Salary:** $240,000.0 - $320,000.0
- **Contract:** Permanent contract
- **Skills:** Artificial Intelligence, Amazon Web Services, Bash Shell, Cursor, Python (Programming Language), Reliability Engineering, TypeScript, Scripting, Istio, Delivery Pipeline, Claude Code, Agentic-AI, AI Platforms, Git Flow, Kubernetes
- **Published:** November 4, 2026
- **Apply:** https://www.thejobnetwork.com/job/f1230c02-2dbd-4e5e-afaf-422a23202732/staff-platform-reliability-engineer-agentic-ai-san-francisco

## About the Role

* 5-10 years of experience as an IC platform engineer or site reliability engineer
 * Hands-on with AWS, Kubernetes, service mesh, GitOps and infrastructure-as-code
 * Scripting/coding in TypeScript, Python and/or Bash
 * Comfortable using AI-native tools (Claude Code, Cursor) day to day

## Description

We're looking for a Staff Platform and Reliability Engineer with 5-10 years of experience to be the dedicated owner of the reliability and security layer behind the company's agentic AI platform. As they scale customers, grow the team and move from V5 to V6, they need a hands-on, senior-most IC who keeps AI in production running smoothly for 100+ banks and credit unions. Today that work is spread across engineering, support and delivery. You'll be the person it all rolls up to.

What you'll do

 * Get into the infrastructure and delivery pipeline early to make sure fixes ship the right way
 * Find reliability and delivery gaps, present a plan to the CTO and CEO, and close those gaps
 * Make measurable improvements to uptime and deployment speed without ever compromising security
 * Own SLOs, incident response, observability and DR for the AI platform, held to a 99.99% bar
 * Secure the AWS/Kubernetes platform and produce compliance evidence (SOC 2, NCUA/FFIEC, GLBA)