2 hours ago
Base Salary
$204k - $352k/yr
Responsibilities
- Design agentic systems by determining task decomposition, agent context, agent counts, and model assignment.
- Improve model accuracy through context design, self-verification, voting, consensus, and adaptive agent scaling.
- Measure output quality using sampling, automated verification, precision, and recall.
- Optimize cost and latency through model routing, caching, early stopping, and smaller or fine-tuned models.
- Convert one-off experiments into reusable workflows on Ramp’s orchestration stack.
- Evaluate new models, inference setups, and training approaches and productionize effective solutions.
- Own applied AI roadmaps and production systems with limited oversight.
Requirements
- Experience building and shipping applied AI systems and LLM applications.
- Hands-on experience with multi-agent or high-fan-out LLM workloads, including parallel agents, model-based map-reduce, or large-batch inference.
- Strong Python engineering skills and experience building concurrent, distributed systems for production.
- Ability to define desired outputs, distinguish useful signal from agent noise, and make sound scaling decisions.
- Experience measuring cost, yield, false-positive rates, and the impact of system changes.
- Ability to own a roadmap and production system with little oversight.
- Clear written communication.
- Preferred experience building agent orchestration or job systems with Ray, Temporal, Modal, or custom technologies.
- Preferred experience using LLMs to search codebases, document sets, logs, or other large corpora.
- Preferred experience with post-training or hosting open-source models for high-volume inference.
- Distributed systems background and publicly reviewable work such as an agent framework, open-source project, technical write-up, or paper.
Benefits
- Flexible PTO, centralized home-office equipment ordering, a health and wellness stipend, intra-office travel budget, and weekly coffee stipend.
- United States employees receive full medical, dental, and vision coverage for themselves with partial dependent coverage, One Medical membership, 401(k) with employer match, fertility HRA, paid parental leave, pet insurance, in-office perks, and relocation coverage to NYC or San Francisco if needed.
- Canada employees receive group medical, dental, vision, life, AD&D, disability, fertility drug, retirement, parental leave, employee assistance, and virtual care benefits.
- United Kingdom employees receive private medical insurance, virtual GP and at-home care, workplace pension, and paid parental leave.
- The role is a full-time Ramp position with benefits available globally; work locations and applicable benefits vary by country.
Tech Stack
Categories
About Ramp
Ramp builds a finance operations platform for businesses, combining corporate cards with expense management, bill pay, accounts payable, travel, and accounting automation. Founded in 2019 and headquartered in New York, the privately held company’s systems handle over $200B in annualized spend across 70,000+ companies. Its business model blends card interchange with software that helps finance teams control and automate spending.
