The role
- COMP
- $150K - $350K
- EQUITY
- Highly Competitive Equity
- LOCATION
- New York
- WORKPLACE
- On-site
- EXPERIENCE
- 5 - 15 years
- VISA
- None, Visa transfers
- STACK
- React, TypeScript, Python, PostgreSQL
- INDUSTRY
- AI, B2B, Finance, Financial Services, Fintech
/roles — ROLE_329
Member of Technical Staff - Product Engineering
Accounting AI company building long-running agents that take on complex finance and tax work
The company
Accounting-AI company whose agents do real accounting work end-to-end, used by top firms across client accounting, tax, and audit.
- STAGE
- scale-up
- FUNDING
- $140M+ raised
- TEAM
- 100+ people
- FOUNDED
- 2023
- BACKING
- backed by Khosla Ventures
JD — the work
About the role
Engineers here work in pods organized around goals rather than fixed functional teams, and the pods reshuffle each quarter as priorities change and the team grows. One week could go to shaping an agent's context model, the next to writing pipelines that load its state. Some engineers move between infrastructure and agent-facing product work from quarter to quarter, while others go deep on one technical area. The role is on-site in New York.
What you'll do
- Build product features across a React, TypeScript, Python, and PostgreSQL stack
- Work on agent engineering such as context design and tool design
- Contribute to the agent platform, including harnesses and evaluation systems
- Improve core infrastructure and the external data feeds agents need to be accurate and fast
- Help the internal AI team create agents, shared context, and knowledge tooling for the company's own recruiting, sales, and engineering
- Tackle open questions like managing agent state over hours-long runs and choosing the right abstraction level for tools
- Pull useful signal from long agent trajectories and tune evaluation judges on subjective tasks
What they're looking for
- 5+ years of software engineering experience, typically across the full stack
- Proficiency with React, TypeScript, Python, and PostgreSQL
- Comfort with shifting problems and moving between product and infrastructure work
- Interest in the hard problems of building with nondeterministic agent systems