Staff Engineer, Agentic Productivity and Infrastructure
Staff-level engineer to own internal infrastructure and agentic productivity tools that accelerate SDLC, platform operations, and developer experience for a small AI underwriting startup.
About the job
What you’ll do
- Streamline the build-and-ship loop. Design internal systems and agents that accelerate how we write, review, test, and ship code - turning manual engineering toil into automated, agent-assisted workflows.
- Automate platform operations. Build the systems that keep the platform healthy with less human effort - CI/CD, observability, alerting, and agent-assisted monitoring and incident response.
- Continually improve our internal developer platform. Create the paved roads, tooling, and environments that let every engineer ship faster and more safely, and that make our agentic workflows reliable and repeatable.
- Seek leverage. Identify where automation and agents pay off most across the engineering org, prototype quickly, and measure the impact on velocity and reliability.
- Elevate the team. Establish the internal tooling patterns, libraries, and standards the rest of the team builds against. Mentor and recruit the engineers who’ll work alongside you.
Who you are
- You’re deeply customer-focused. But in this case, your “customers” are your engineering teammates. You care about their workflows and the outcomes your tools produce, and you measure success by how much faster and safer the org ships.
- You’re a builder at heart. You’ve shipped meaningful systems used by real people. You likely have side projects, strong opinions about technology, and genuine curiosity about where AI is heading. You are a creator.
- You operate with urgency and ownership. You move quickly without sacrificing reliability or trust. You proactively identify problems, communicate clearly, and drive solutions.
- You elevate the people around you. You bring strong engineering judgment, high standards, and collaborative energy. Teams become stronger when you’re involved.
- You’re excited by difficult systems problems. Developer experience, automation, agent reliability, observability, and AI-assisted operations genuinely interest you.
What you’ll bring on the technical side
- Strong proficiency in Go, Python, and/or TypeScript is a bonus, but we trust that great engineers can learn on the job.
- Experience building developer tooling, internal platforms, CI/CD, or DevOps/SRE systems in production.
- Hands-on experience building with LLMs or agents - or strong conviction and curiosity about applying them to engineering workflows.
- Comfort with infrastructure and operations - Infrastructure-as-Code (Terraform/Pulumi), observability, and the practices that keep systems healthy under load.
- A track record of leading a technical surface end-to-end. Bonus if you’ve built agentic developer tooling or internal automation that measurably moved a team’s velocity.
Compensation and benefits
- Competitive compensation calibrated to senior/principal-level engineers in San Francisco
- Meaningful equity ownership
- Full medical, dental, and vision coverage
- 401(k) with company match
- Flexible vacation policy
- Parental leave
- Learning and professional development support
Skills
Go, Python, TypeScript, CI/CD, DevOps, SRE, Terraform, Pulumi, Observability, LLMs, Infrastructure As Code
Similar jobs
DevOps / SRE jobs
Anthropic
San Francisco, CAStaff-level site reliability engineer responsible for safely deploying and operating safeguards infrastructure across model releases and cloud platforms. The role emphasizes production change management, high-stakes incident response, and automating manual launch and validation processes.
Polymarket
New York, NY
Staff Infrastructure Engineer responsible for designing and operating scalable infrastructure for growth systems, including onboarding, referrals, and user acquisition. The role requires 7+ years of production infrastructure experience, strong reliability instincts, and independent judgment in a high-autonomy environment.
Fortanix
Santa Clara, CA
Leads the architecture, development, and operation of cloud, Kubernetes, on-premises, and hybrid infrastructure, while building developer platforms and CI/CD automation. Requires at least six years of infrastructure or related engineering experience, deep Kubernetes expertise, strong programming skills, and technical leadership.
Scale AI
San Francisco, CA
Own the network architecture and standards for a multi-cloud enterprise AI platform deployed across Kubernetes environments and customer-controlled networks. The role requires deep cloud and Kubernetes networking expertise, strong security fundamentals, and the judgment to establish scalable, supportable connectivity patterns.
Motive
Buffalo, NYStaff Platform Engineer will build and improve automated delivery pipelines, developer environments, infrastructure, and release systems across the engineering organization. The role requires 6+ years of engineering experience, a bachelor’s degree, and expertise with CI/CD, cloud infrastructure, containers, and infrastructure as code.