LawnStarter
Staff Software Engineer, Product — Montevideo (Remote)
Own outcomes. Lead with engineering judgment. And ship end-to-end in a product org that’s built for momentum. At LawnStarter, you’ll be the technical anchor for an initiative—partnering tightly with a PM and designer—while AI coding agents help your small, senior team move faster without sacrificing quality.
This is a remote role for candidates located in Montevideo, Uruguay.
About LawnStarter
LawnStarter is the nation’s leading on-demand marketplace for lawn care and outdoor services, with $100M+ in annual bookings. We’re expanding beyond lawn care to become a one-stop shop for all home services, operating across three brands—LawnStarter, Lawn Love, and Home Gnome—on a single shared platform.
About Engineering at LawnStarter
We build in small, focused initiative teams. Each Product Engineer works alongside a PM and a designer, supported by an Engineering Manager who helps you grow. You’ll also collaborate closely with engineers across adjacent initiatives in a shared codebase.
Ownership is real. Teams own whether the work moves the metric—not just whether code lands in a PR.
AI coding agents are a force multiplier here. They give a small, senior team leverage to ship more, faster, and at a higher bar for quality. We hire engineers who are wired for ownership and energized by shipping to a real marketplace—with customers and pros on both sides.
About The Role
As a Staff Software Engineer, Product, you’ll serve as the engineering anchor of an initiative. You’ll shape the problem, decide the technical approach, direct AI agents to implement much of the code, ship to production, and—together with your team—own the outcome.
You won’t be measured by lines of code merged. You’ll be measured by impact.
- When an agent can ship safely, your job is to ensure it’s done right and that the initiative metric moves.
- When the work demands sensitive, careful craft, you’ll write the code yourself.
What You’ll Do
- Ship end-to-end: from problem-framing and technical decision-making through production release and post-launch metric review.
- Partner like a product engineer: collaborate daily with your PM on scope and tradeoffs, and with your designer on UX decisions and in-tool prototyping.
- Operate with autonomy: make most technical calls yourself, with architect review for significant architectural decisions and fast input from engineering peers.
- Lead AI agent workflows: direct agents using prompts, guardrails, evals, and review loops so the output is production-ready.
- Guarantee quality: hold the same bar for agent-authored code as you would for human-authored code—correctness, security, performance, and observability.
- Drive initiative ownership: present results 2–4 weeks post-launch with your team and answer the “did it work?” question with data.
What You’ll Own
- The technical approach for your initiative:
- Architecture and system design
- Data model decisions
- Integration choices
- Rollout plan
- Observability strategy
- Rollback strategy
- Implementation quality that enables safe agent shipping:
- Prompts and conventions
- Guardrails
- Evals and test strategy
- Review loop that catches issues before merge
Most implementation will be agent-authored. You’ll be accountable for it.
- Cross-functional partnership:
- Daily working contact with your PM (scope, tradeoffs)
- Designer collaboration (UX decisions, prototyping)
- Regular collaboration with engineering peers across initiatives
- Weekly check-ins with your Engineering Manager
- The initiative outcome:
- The metric your initiative was built to move (e.g., conversion, retention, pro-funnel KPI, unit economics shift)
- Post-launch results review with your PM 2–4 weeks after release
Problems You’ll Solve
- Leading AI agents at a staff-level quality bar
Most code on your initiative will be authored by AI agents. The craft is ensuring agents ship like a senior engineer:- Prompts that encode our conventions
- Evals that catch issues before merge
- Tests that exercise edge cases
- Observability that detects regressions before customers do
Your challenge: build a workflow that lets a small team ship far more than its size suggests.
- Owning decisions with high autonomy
You’ll have real latitude to make and document technical calls quickly:- Architect review on major architectural decisions
- Peer pressure-testing to validate your thinking
Your challenge: move fast, keep the team aligned, and remain accountable to the outcome.
- Shipping outcomes, not features
Each initiative is measured by a metric—not activity. You’ll scope work to move the metric, decide what not to build, and follow up after launch:- Conversion rate improvements
- Retention curve shifts
- Pro-funnel KPI movement
- Unit-economics impact
Your challenge: have the discipline to measure impact 2–4 weeks post-launch.
What Success Looks Like (Year 1)
- Initiative outcomes hit: ship 3–4 initiatives end-to-end, with at least two clearly moving their metric (backed by post-launch review).
- Agent workflow travels: your prompts/evals/review loop become reusable patterns adopted by peers on other initiatives.
- Faster cycle time: meaningfully reduce the median time from problem-framing to first production rollout on your initiatives.
- Quality holds: no customer- or pro-facing regressions traceable to agent-authored code that slipped through review.
- Visible leverage: peers reference your artifacts—runbooks, evals, agent workflows, and post-launch write-ups.
What We’re Looking For
- AI-native
You ship daily with tools like Claude Code, Cursor, Codex, or equivalent. You have strong opinions about:- Prompting strategies
- Evals and agent loops
- Review workflows
- When to let the agent run vs. when to write yourself
- Operating at a lead/staff level
Whatever your current title, you’re the person making the call, shipping the hard thing, and standing behind whether it worked. - Outcome-driven mindset
You think in “did the metric move?” and “did the experience improve?” You read dashboards and own the answer after launch. - A strong horizontal partner
You collaborate effectively across product and engineering:- Bring engineering judgment to product calls
- Bring product judgment to engineering calls
- Hold your own with PMs and designers
- Decisive—and documented
You make architecture/data-model/rollout decisions quickly, write them down, get fast input, and move. - A force multiplier
Your impact compounds beyond your initiative through reusable artifacts:- Agent workflows
- Evals
- Runbooks
- Post-launch reviews
- Customer- and pro-minded
This is a real marketplace with real people. You care about outcomes for both sides.
Good to Know
- Individual-contributor role with room to grow. People management sits with the Engineering Manager, but management is an open door for those who want it.
- Product engineering, end-to-end: you ship to move metrics; platform/architecture work happens inside the initiative when needed.
- Hands-on with a high bar: agents handle much of the implementation—your job is judgment, safety, design thinking, and accountability.
- Shipping to a live marketplace: with $100M+ in bookings, customers and pros use what you ship within the same week.
Tech You’ll Touch
- AI agents: Claude Code, Cursor, Codex, internal agent stack, MCP servers, evals tooling
- Backend: PHP / Laravel
- Frontend: TypeScript / React / React Native (customer & pro apps, web and mobile)
- Data: Redshift, dbt, Segment, Airflow
- Infra: AWS, Datadog, Sentry, GitHub Actions
- Documentation & process: Brain (Claude Code skills + docs repo), Confluence, Jira
Benefits
- Competitive compensation: USD $80,000–$100,000 annual base
- Work from anywhere
- High ownership and autonomy
- Fast-moving team that loves to build, learn, and grow
Ready to Own the Outcome?
If you have deep skill in at least one of the stacks above and credible production experience working with AI coding agents, we’d love to meet you. You don’t need every box checked—you need the judgment, craftsmanship, and drive to ship impact.
—
To apply for this job please visit remotive.com.