Senior Engineer, Agent Runtime Platform
ABOUT EMBANKMENT
The future of fund management will be executed by AI agents. Humans will define objectives, establish controls, and verify outcomes.
Historically, fund teams relied on manual processes, spreadsheets, and fragmented systems to manage complex workflows. We believe those workflows will increasingly be carried out by AI agents operating within well-defined controls and quality boundaries.
To support that future, we are building an Agent Runtime Platform: the infrastructure that allows AI agents to perform work safely, reliably, and efficiently at scale across fund management.
This platform will become a foundational capability of the company. It will orchestrate agents, manage long-running workflows, provide visibility into execution, and ensure that work can be delegated with confidence across operational domains.
We are looking for a Senior Engineer to help build it.
THE ROLEAs a Senior Engineer, you will design and build core capabilities of the Agent Runtime Platform.
Your mission is straightforward to describe: help create a system capable of running large numbers of AI agents in production while maintaining the reliability, efficiency, and operational excellence expected of any critical platform.
You will work across the platform stack, contributing to architecture, implementation, observability, reliability, security, and cost efficiency. Many of the problems we are solving are still emerging, and we are looking for engineers who enjoy turning ambiguity into working systems.
Examples of questions you may help solve include:
- What should agent execution look like at scale?
- How should agents recover from failures?
- How should long-running work be coordinated?
- How do humans remain in control while delegating increasingly complex tasks?
- How do we ensure agent execution remains cost-efficient, particularly with respect to token usage and model interactions?
You will contribute to architectural decisions, drive initiatives from concept to production, and help other engineers build successfully on top of the platform.
WHAT WE'RE LOOKING FORFirst and foremost, we are looking for a strong engineer who enjoys solving difficult distributed systems problems.
Technical Execution
You have:
- Delivered significant backend, platform, or infrastructure projects.
- Owned systems that are relied upon by other engineers or teams.
- Demonstrated strong engineering judgment and sound technical decision-making.
- Taken projects from design through production operation.
- Diagnosed and resolved complex production issues.
Platform, Distributed Systems, and Reliability
You have experience building and operating systems such as:
- Internal developer platforms.
- Infrastructure services.
- Workflow orchestration systems.
You are comfortable reasoning about:
- Reliability and fault tolerance.
- Concurrency and distributed execution.
- Scalability and performance.
- Security and isolation boundaries.
- Observability and operational excellence.
- Infrastructure efficiency and cost optimization.
You care deeply about building systems that are resilient, maintainable, and easy to operate.
AI-Native Engineering
You actively use AI agents as part of your daily workflow.
You are comfortable:
- Delegating implementation work to agents.
- Reviewing and validating AI-generated code.
- Using agents for research, design, debugging, and implementation.
- Operating in an environment where AI is a core part of the engineering process.
When you need code written, your instinct is to direct an agent, not open an editor.
WHAT SUCCESS LOOKS LIKE AFTER 6 MONTHS
After your first six months, you will have:
- Established yourself as one of the technical leaders of the Agent Runtime Platform and earned the trust of engineers across the company.
- Delivered the first production version of the Agent Runtime Platform and successfully onboarded early teams and workflows.
- Enabled product teams to begin building agents and automation on top of the platform rather than creating bespoke solutions.
- Identified and addressed the most significant technical bottlenecks discovered through real-world usage.
Success in this role is measured by the leverage you create: how effectively the platform enables agents, engineers, and operational teams to accomplish more than they could before.