204K–352K USD / year
Research Engineer, Agentic Systems
AIRemote — United States
Published on 2026-11-18
These details were extracted automatically from the original listing. They may not be complete or fully up to date — it's worth checking the original job post.
About this role
Build and operate high-fan-out, multi-agent AI systems that coordinate many agents to produce useful, verified results. Own workflows from prototype to production, improving output quality while controlling cost and latency.
About the company
Ramp is a financial automation platform that provides companies with tools to manage expenses, optimize procurement, and improve financial workflows. It serves businesses looking to streamline their financial processes and enhance visibility into spending.
The team
Ramp Labs, Ramp's AI research and engineering group.
Stack
PythonRayTemporalModal
What you'll do
- Design how work is divided among agents, including context, model selection, and agent count.
- Improve accuracy through context design, verification, voting, and consensus.
- Measure output quality using sampling, automated verification, precision, and recall.
- Reduce cost and latency with model routing, caching, early stopping, and smaller or fine-tuned models.
- Turn experiments into reusable production workflows.
- Evaluate new models, inference setups, and training approaches.
What we're looking for
- Experience building and shipping applied AI systems and LLM applications.
- Hands-on experience with multi-agent or high-fan-out LLM workloads.
- Strong Python skills and experience building production-grade concurrent, distributed systems.
- Good judgment in defining and assessing useful outputs.
- Measure cost, yield, false-positive rate, and the impact of changes.
- Able to own a roadmap and production system with little oversight.
- Clear written communication.
Nice to have
- Experience with agent orchestration or job systems such as Ray, Temporal, Modal, or custom systems.
- Experience using LLMs to search large codebases, document sets, logs, or other corpora.
- Experience post-training or hosting open-source models for high-volume inference.
- Distributed systems background.
- Public work such as an agent framework, open-source project, write-up, or paper.
Benefits
- Equity offered.
- Flexible PTO.
- Medical, dental, and vision coverage for employees, with partial dependent coverage.
- 401(k) with employer match.
- Up to 16 weeks of paid parental leave for birthing and bonding, or 8 weeks for bonding only.
- Home-office equipment ordering and a health and wellness stipend.
