Ramp Research Engineer, Agentic Systems responsible for building applied AI systems and LLM applications with multi-agent or high-fan-out workloads. Focuses on model accuracy, cost, latency, and quality measurement.
Responsibilities
Most agent work today is one agent, one trace, and a person reads the result. We're building systems where that stops working: thousands of agents fanned out over a large search space, each returning partial results, with an orchestrator that turns all of it into something useful: hundreds of merged PRs, a dataset, the input to another system, or something nobody has built yet.
You'll design and run those systems: how work gets split, how agents coordinate, how results get deduplicated, verified and ranked, and what it all costs. The problems are general (agent swarms, agentic map-reduce, long-running fan-out workflows) and you'll own them from prototype to production.
Decide how the work gets done: how to break a problem down, what each agent sees, how many agents to run, and which model handles which step
Squeeze accuracy out of the models: context design, self-verification, voting and consensus across agents, and knowing when more agents stop helping
Measure quality without reading every trace: sampling, automated verification, and precision and recall on the final output
Drive down cost and latency per useful result: model routing, caching, early stopping, and smaller or fine-tuned models where they hold up
Turn one-off experiments into reusable workflows on our existing orchestration stack
Evaluate new models, inference setups and training approaches, and bring in what works
Qualification
Strong engineering in PythonJudgment about outputThe habit of measuringOwnershipClear written communicationUsed LLMs to search large spacesDistributed systems backgroundPublic work we can look atPublic work such as agent frameworks
Required
Experience building applied AI systems and LLM applications that shipped
Hands-on experience with multi-agent or high-fan-out LLM workloads: parallel agents, map-reduce over models, large batch inference
Strong engineering in Python; you build concurrent, distributed systems that hold up in production
Judgment about output: you decide what the end result should look like before you scale the swarm, and you can separate signal from agent noise
The habit of measuring: cost, yield, false-positive rate, and whether a change actually helped
Ownership: you can run a roadmap and a production system with little oversight
Clear written communication
Built agent orchestration or job systems (Ray, Temporal, Modal or custom)
Used LLMs to search large spaces: codebases, document sets, logs or other large corpora
Post-training or hosting open-source models for high-volume inference
Distributed systems background
Public work we can look at: an agent framework, an open-source project, a write-up or a paper
Preferred
Built agent orchestration or job systems (Ray, Temporal, Modal or custom)
Used LLMs to search large spaces such as codebases or document sets
Post-training or hosting open-source models for high-volume inference
Distributed systems background
Public work such as agent frameworks, open-source projects, write-ups, or papers