You will build the core agent harness—the runtime turning LLMs into reliable, extensible agents. This includes managing the execution lifecycle, tool calling, and trust boundaries. You’ll design abstractions for memory, context, and multi-agent collaboration, ensuring the system is robust and high-performing for knowledge workers who need proactive AI support daily.
Software Engineer: AI Harnesses & Tooling at fast-growing AI productivity startup
Join a well-funded AI productivity startup as a founding engineer to build the foundational agent harness and runtime that transforms Large Language Models into reliable, proactive tools for knowledge workers. Led by a team that previously scaled massive agent ecosystems and internal productivity suites at elite data and fintech unicorns, you will design the core runtime, complex tool-calling loops, and secure sandboxed execution environments that define the next generation of multi-agent orchestration and personal AI automation.
Want to apply for this role?
C
Jack finds you jobs at companies like Confidential company. Talk to Jack to get considered for roles that fit what you're great at.
Location
Remote
Compensation
Not Disclosed
Company
Confidential company
Role overview
About the company
Fast-growing AI productivity startup
What you will do
- Design and build the agent runtime covering dispatch, execution lifecycle, tool-calling loops, and error handling.
- Develop a microkernel-style extension system that allows users and agents to customize the harness for specific problems.
- Implement robust trust boundaries, including sandboxed execution, permission models, and secure credential management.
Who this is a fit for
- Deep expertise in agent runtimes and LLM APIs at the protocol level, with a strong understanding of how tool-calling loops function internally.
- Exceptional systems instincts regarding failure modes, resource limits, isolation, and concurrency before feature development.
- Experience building non-leaky abstractions and ideally working with systems languages like Rust or Go alongside TypeScript.
Why this role is remarkable
- Join a founding-team environment building the infrastructure that makes agentic AI useful for non-technical power users through a proactive desktop application.
- Backed by top-tier VCs and led by founders who previously scaled massive agent ecosystems and productivity suites at elite data and fintech unicorns.
- Solve complex systems problems at the intersection of LLMs and runtime execution, including sandboxing, streaming, and multi-agent collaboration.
How Jack & Jill work together
I get to know what you’re great at, then find roles you’d never find yourself.Ok, I'll go first. I'm Jack, an AI that gets to know you on a quick call, learning what you're great at and what you want from your career. Then I help you land your dream job by finding unmissable opportunities as they come up, supporting you with applications, interview prep, and moral support.
I recruit from Jack’s network and make the intro when I spot a great match.And I'm Jill, an AI Recruiter who talks to companies to understand who they're looking to hire. Then I recruit from Jack's network, making an introduction when I spot an excellent candidate.
Jack gets to know what you're great at and what you want next, then searches 15 million jobs daily and helps you discover roles at companies like this.
Meet Jack
What happens next?
Jack’s an AI agent for job searching and career coaching. He works for you.
Jill is the AI recruiter working for the company. She recruits from Jack’s network.
If your profile’s a match and Confidential company wants to meet, Jill will make the intro. In the meantime, Jack will send you excellent alternatives.