Member of Technical Staff
Engineering · Posted 5 months ago
We are seeking an engineer with experience building and maintaining distributed systems and LLM infrastructure. You should be comfortable with container orchestration tools (e.g., Kubernetes) and message-driven architectures (e.g., SQS, Kafka). A proven track record of running LLM workloads at scale is essential for th...
- Way of working
- Hybrid
- Location
- New York, Brooklyn, NY
- Pay range
- $200,000 to $280,000
- Level
- Staff
- Experience
- 3+ years
- Type
- Full time
- Visa sponsorship
- Not offered for this role
- The company
- Data Infrastructure and Analytics · under 20 people
Skills that matter here
What you would be doing
- Agent orchestration at scale. Hundreds of agent runs at once, each with its own stateful environment. 100M tokens per minute across the fleet. You own the dispatch layer: SQS, concurrency control, failure handling.
- Environment and task design. We need environments that feel real and scenarios that actually push agents to their limits. You'd figure out how to build new evaluations and design the tasks that test what matters, not just what's easy to measure.
- New frontiers. The agent evaluation space is moving fast. You'd stay on that edge, supporting new environment modalities and shipping integrations with external orchestration frameworks.
The full description
What we're looking for
We are seeking an engineer with experience building and maintaining distributed systems and LLM infrastructure. You should be comfortable with container orchestration tools (e.g., Kubernetes) and message-driven architectures (e.g., SQS, Kafka). A proven track record of running LLM workloads at scale is essential for this role.
What you'll do
- Agent orchestration at scale. Hundreds of agent runs at once, each with its own stateful environment. 100M tokens per minute across the fleet. You own the dispatch layer: SQS, concurrency control, failure handling.
- Environment and task design. We need environments that feel real and scenarios that actually push agents to their limits. You'd figure out how to build new evaluations and design the tasks that test what matters, not just what's easy to measure.
- New frontiers. The agent evaluation space is moving fast. You'd stay on that edge, supporting new environment modalities and shipping integrations with external orchestration frameworks.
Interested in this one?
There is no apply button here on purpose. Tell us about yourself, we book a short call, and if this role fits we walk you through the company and ask before anything is sent. Always free for you.
Tell us about you