Confirmed on the employer's own hiring board on Nov 18, 2026. First seen by Alion on Nov 17, 2026. Sage scores A on the Alion truth index.
We're investing heavily in AI. Our AI Infrastructure team is building the platform that lets AI agents take engineering intent and carry it through the software development lifecycle end to end: planning, coding, testing, review and merge, with controls that let each team increase agent autonomy as trust builds.
The team designs and runs everything that makes that work: orchestration, isolated development environments, agent identity and access, model access and routing, context and memory, evaluation, and the feedback loops that make agents better over time. It's an unusual mix of distributed systems, systems engineering and applied AI, much of it not yet done at enterprise scale, and you'll be building it from the early stages with engineering teams across Sage as your first users.
*** Please note that this role is hybrid and requires working 3 days a week from our San Jose office. ***
Responsibilities
- Build and ship well-scoped features in platform components such as workflows, sandboxes, gateways, evaluation tooling or developer SDKs.
- Write design notes for your work and take part in design reviews.
- Write clean, tested code, with the logging, metrics and traces needed to support it in production.
- Build integrations with Jira, GitHub, CI/CD and Slack, and help teams onboard their repositories.
- Investigate agent failures and production issues, and fix the root cause.
- Take part in code reviews, on-call and incident reviews.
- Keep up with fast-moving AI tooling and share what you learn with the team.
What You'll Own
- Implementation and testing of your assigned work, raising risks and questions early, and keeping your code production-ready.
What We're Looking For
- Software engineering experience, ideally with hands-on experience using LLM-powered tools or agents.
- Solid programming skills in one or more of Python, TypeScript, Go, Java or Rust.
- A good grasp of system and API design, data modelling and testing.
- Experience building and deploying services in the cloud with containers; exposure to Kubernetes and infrastructure as code.
- Understanding of async processing, queues and handling failures in distributed systems.
- Hands-on experience building with LLM APIs: tool use, prompts, RAG or simple agents. Side projects count.
- Usage of AI coding tools day to day.
In this location, the base salary range is $120,000 to $150,000, depending on experience.

