Agentic Systems Engineer
You build multi-agent superintelligence (SI) systems on client documents and data. You design the planner, the specialist agents and the audit step that checks every citation against its source, and you record every run so it can be replayed. Each system passes tests built from the client's own material before it goes live.
Duties
- Design multi-agent systems in which a planner splits a question and specialist agents each work one part.
- Build typed tool interfaces so each agent reaches only the tools and data its part needs.
- Add policy checks before consequential tool calls, with scoped credentials and an approval step where a person must decide.
- Write the audit step that compares every citation with the logged evidence and sends unsupported claims back for rework.
- Record every run with its inputs, tool calls, outputs and pinned model versions, so it can be replayed.
- Build evaluation sets from the client's own material and run them in CI on every change.
- Measure answer quality, citation accuracy and failure cases for each model family and version.
- Deploy systems in an environment the client controls and document how its team runs them.
What you bring
- 3+ years building production software in Python or TypeScript.
- Experience building applications on LLMs, including tool calling and retrieval.
- Experience designing typed interfaces and validating structured outputs.
- Experience writing automated tests and running them in CI.
- Clear technical writing.
Nice to have
- Experience building MCP servers or other tool interfaces for agents.
- Experience with Pydantic, Zod or JSON Schema.
- Experience with retrieval over large document sets.
- Experience deploying services on Kubernetes.
Pay and benefits
$124,000 to $201,000 a year
Full-time W-2 employment with health insurance, a retirement plan and paid leave.
No application deadline. We accept applications for this role on an ongoing basis.
Location
Remote, United States
Apply
We review applications as each team grows and contact you when there is a match.
Rillor is an equal opportunity employer. We consider qualified applicants without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, veteran status or any other status protected by law.
If you need an accommodation to apply, email careers@rillor.com.
Notices
Trademarks. NVIDIA, AMD, Ceph, Kubernetes and related product names are trademarks of their owners and are used only to identify products. No affiliation or endorsement is implied.