Senior Software Engineer, Agent Frameworks
Thealleninstitute · Seattle, WA · Posted Jul 2, 2026
Apply on company site Track it in JobSkout
Persons in these roles are expected to work from our offices in Seattle. On-site requirements vary based on position and team. If you have questions about on-site work arrangements for this role, please ask your recruiter.
Our base salary range is $126,000 - $189,000, and in addition we have generous bonus plans to provide a competitive compensation package.
Who You Are:
The Allen Institute for AI (Ai2) is hiring a Senior Engineer to build the foundational architecture behind AI research agents that explore and reason over scholarly literature. You'll design the systems that define how agents, tools, and services interact, creating SDKs, APIs, and execution frameworks that enable researchers to build, evaluate, and scale intelligent systems. You'll contribute to the agent architecture, build infrastructure for sandboxed execution and benchmarking, and create evaluation frameworks that measure component performance. You're a seasoned engineer who thrives in greenfield environments, excels at building robust developer-facing infrastructure, and is energized by making complex distributed systems feel simple.
Who We Are:
The Agentic Applications team builds open, production-grade AI systems that power scientific discovery. We focus on developing intelligent agents that help researchers explore literature, synthesize knowledge, and accelerate their work across real-world scientific use cases. The team combines strong engineering practices with close collaboration across Ai2's product and research orgs to deliver tools used by millions of researchers and developers worldwide.
Your Next Challenge:
The essential functions include, but are not limited to the following:
Design and build the frameworks, SDKs, and execution surfaces that define how agents, tools, and services interact across our research platform
Build infrastructure for sandboxed agent execution, enabling researchers to safely run, inspect, and iterate on agent workflows at scale
Design and maintain evaluation and benchmarking frameworks that measure the performance of individual agent components and end-to-end systems
Develop the abstractions and developer-facing tooling that let research scientists build, compose, and deploy agents without owning the underlying infrastructure
Drive continuous improvements in reliability, observability, and cost-efficiency across the systems agents run in and depend on
Engage in the entire software development lifecycle, from ideation and design to implementation and testing to deployment and operational support, with a strong sense of ownership for results
Collaborate across engineering and research teams to ensure maintainability, test coverage, and robust deployment
Communicate effectively across engineering, product, and research teams to align priorities and drive projects to completion
What You’ll Need:
Bachelor's degree and 8+ years of technical experience; relevant experience may substitute for education
Strong Python engineering skills, with experience building production services and developer-facing tools
Experience designing SDKs, APIs, or frameworks that other engineers built on top of and adopted
Hands-on experience building or operating agentic systems – agent orchestration, tool integration, sandboxed execution, memory management, or the surfaces agents run in and consume
Experience designing evaluation or benchmarking infrastructure that measures system or component performance
Experience with cloud infrastructure (AWS, GCP, or similar), containerization, and deployment automation
Strong communication skills and a sense of ownership for results
Physical Demands and Work Environment:
The physical demands described here are representative of those that must be met by a team member to successfully perform the essential functions of this position. Reasonable accommodations may be made to enable individuals with disabilities to perform the functions.
Must be able to remain in a stationary position for long periods of time.
The ability to communicate information and ideas so others will understand. Must be able to exchange accurate information in these situations.
The ability to observe details at close range.
Can work under deadlines.
A Little More About Ai2:
Ai2 is a Seattle based non-profit AI research institute founded in 2014 by the late Paul Allen. Our mission is building breakthrough AI to solve the world’s biggest problems. We develop foundational AI research and innovation to deliver real-world impact through large-scale open models, data, robotics, conservation, and beyond.
In addition to Ai2’s core mission, we also aim to contribute to humanity through our treatment of each member of the Ai2 Team. Some highlights are:
We are a learning organization – because everything Ai2 does is ground-breaking, we are learning every day. Similarly, through weekly Ai2 Academy lectures, a wide variety of world-class AI experts as guest speakers, and our commitment to your perso…