Research infrastructure
Research Engineer
This role lives at the intersection of research and infrastructure. You will build and maintain the systems that make AI visibility research possible at scale — prompt runners, answer capture pipelines, normalization layers, and the internal tooling that keeps quality high as models and assistants change.
Role summary
Build the systems that run strategic prompts at scale, capture raw model output reliably, and feed clean data into evaluation pipelines.
Why this role exists
The research pipeline is the foundation everything else sits on. Without reliable prompt execution and output capture, the product has nothing to evaluate. We need someone who treats the pipeline as a product, not just plumbing.
First 90 days
Map and document the current prompt execution and capture pipeline end to end.
Why this role exists
The research pipeline is the foundation everything else sits on. Without reliable prompt execution and output capture, the product has nothing to evaluate. We need someone who treats the pipeline as a product, not just plumbing.
What you will work on
- Design and operate prompt execution systems across multiple AI assistants at scale.
- Build output capture, normalization, and storage layers that handle variability in model behavior.
- Own the reliability and observability of the research data pipeline end to end.
- Work closely with the research team to translate evaluation requirements into efficient system behavior.
What a strong fit looks like
- Strong systems and backend engineering instincts applied to data pipelines and async workloads.
- Experience building reliable, observable systems that handle high cardinality and partial failures gracefully.
- Comfort reasoning about LLM output formats, rate limits, latency, and prompt execution logistics.
- A product mindset: you treat the pipeline as something users depend on, not just infrastructure.
What will excite you here
- Building the infrastructure that makes serious AI research operationally possible.
- Owning reliability for a data layer that directly determines product quality.
- Working on a system that touches every corner of the product.
First 90 days
- 01Map and document the current prompt execution and capture pipeline end to end.
- 02Identify and fix the top two reliability or observability gaps in the research data path.
- 03Ship at least one improvement that materially reduces the cost or latency of a core research workflow.
Hiring process
The process is intentionally short, direct, and anchored in the real work.
- 1
Apply
Send us your background, relevant work, and why this role makes sense for you.
- 2
Foundational conversation
A focused conversation about your work, your judgment, and the role itself.
- 3
Role-specific deep dive
A discussion or exercise that looks like the actual work more than a generic interview loop.
- 4
Founder conversation
A final conversation on standards, ambition, and what success would look like here.
- 5
Decision
We close the loop clearly and move quickly once there is conviction.
Need context before you apply? [email protected]
Research Engineer
We are not taking applications for this role yet. We will update this page when it opens.
Questions in the meantime? Email [email protected].