SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: CAD 154,700 - 200,200 / annual
Thumbtack is building internal systems and platforms that power the company at scale. The Business Applications team is expanding its foundation into a broader internal AI platform, creating shared APIs, reusable integration patterns, and safe, auditable capabilities for business-critical actions.
In this role, you will own the product surface that makes AI agent capabilities trustworthy and operationally viable. The core challenge: agents can already take action inside Thumbtack's systems, but business teams need a way to configure what agents are allowed to do, review and correct their work, and understand what happened and why. Without that visibility and control, automation stays stuck in pilots.
You will design and build the interfaces business teams use to configure agents, review their work, approve or correct actions, and understand outcomes. You'll build observability and evaluation tooling that makes agent behavior legible—where it succeeded, where it failed, and whether a change improved performance. Working across the full stack (React, TypeScript, service code, data models), you'll own features end to end from build through test, launch, and iteration. You'll partner directly with business teams to translate operational problems into working software and own the full lifecycle including monitoring and post-launch improvement.
Thumbtack helps millions of people care for their homes through personalized guidance, AI tools, and a hiring platform connecting homeowners with 300,000+ local service businesses across the U.S.
REQUIREMENTS:
- 3+ years of professional software engineering experience
- Strong frontend skills with React and TypeScript, including complex application state and data-dense interfaces
- Solid backend engineering ability (Go, PHP, Python; ability to pick up new languages)
- Working knowledge of relational and non-relational data stores (Postgres, DynamoDB, or similar)
- Real product judgment: ability to evaluate workflows, decide what to build, and identify what to cut
- Interest in problems of non-deterministic systems—uncertainty, partial failure, designing for human correction
- Proven ability to navigate ambiguity, close knowledge gaps, and deliver in evolving environments
