Staff Software Engineer, Product (Belo Horizonte)

Staff Software Engineer, Product (Remote • Belo Horizonte, Brazil)

Own an initiative end-to-end and help LawnStarter scale how we ship—faster, safer, and at a higher bar. As a Staff Software Engineer (Product), you’ll lead the technical direction, partner tightly with PM and design, and use AI coding agents as a force multiplier to deliver production outcomes that move real marketplace metrics. If you’re motivated by impact (not activity) and ready to ship the hard parts with confidence—this is your role.

About LawnStarter

LawnStarter is the nation’s leading on-demand marketplace for lawn care and outdoor services, with over $100M in annual bookings. We’re expanding beyond lawn care to become the one-stop shop for all home services—operating across three brands (LawnStarter, Lawn Love, Home Gnome) on a single shared platform.

About Engineering at LawnStarter

We build in small, focused initiative teams—a Product Engineer working alongside a PM and a designer, supported by an Engineering Manager who helps you grow. You’ll also collaborate closely with engineering peers across adjacent initiatives in a shared codebase.

Everything is outcome-owned. The team measures success by whether the work moves the metric—not by how many changes get merged.

We also use AI coding agents as a leverage multiplier. They help small, senior teams ship more quickly while maintaining a high 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

In this position, you’re the engineering anchor of an initiative. You’ll work as part of a tight product team with your PM and designer, and alongside engineering peers on neighboring initiatives.

You’ll participate in the full lifecycle:

• Shape the problem with your PM and design partner
• Decide the technical approach and define how it will work in production
• Direct AI agents to implement much of the code—while ensuring it meets staff-level quality
• Ship to production with guardrails, testing, and observability
• Own the outcome with your team, including post-launch metric review

You’re measured by impact, not lines of code. When agents can safely ship, you make sure they do it right. When the area is sensitive and requires careful craftsmanship, you write it yourself.

What Makes This Role Exciting

• Ship end-to-end: from problem-framing through production and into the post-launch metric review.
• True product partnership: sit with PM and design and bring engineering judgment into product decisions—and product sense into engineering calls.
• Real autonomy with the right checkpoints: you’ll make most technical calls, with architect review on major architectural decisions and fast peer input.
• Staff-level trust: you’ll be expected to tackle the hard parts, make the call, and stand behind the outcome.

What You’ll Own

• The technical approach
  • Architecture and system design for your initiative
  • Data model decisions
  • Integration choices
  • Rollout plan
  • Observability strategy
  • Rollback approach

  Most decisions are yours. Significant architectural calls go to architect review. You document them—and revisit if the data proves you wrong.

• Implementation quality
  • Prompting strategy
  • Guardrails and safety constraints
  • Evals and automated checks
  • Tests that cover edge cases
  • A review loop designed for production readiness

  Since much of the code is agent-authored, you’re accountable for it—held to the same standard as the rest of the team in the shared codebase.

• Cross-functional partnership
  • Daily collaboration with your PM on scope and tradeoffs
  • Regular collaboration with your designer on UX decisions and in-tool prototyping
  • Ongoing work with engineering peers on adjacent initiatives
  • Weekly check-ins with your Engineering Manager
• The initiative outcome
  • Own the specific metric your initiative is set up to move
  • With your PM, present results 2–4 weeks post-launch
  • Answer the real question: did it work?

Problems You’ll Solve

• Leading AI agents at a staff-level quality bar

  Most of the code on your initiative will be authored by AI agents. The craft is ensuring they ship like a senior engineer wrote it:

  • Prompts that encode our conventions
  • Evals that catch issues before merge
  • Tests that hit edge cases
  • Observability that detects regressions before customers feel them

  Your challenge: build a workflow that lets a small team ship far more than its size suggests.

• Owning decisions with high autonomy

  You’ll move quickly and document your technical calls with architect review for major architecture and peer pressure-testing for alignment.

  Your challenge: move fast without losing accountability to the outcome.

• Shipping outcomes, not features

  Each initiative is measured by a metric—conversion rate, retention curve, pro-funnel KPI, or unit-economics shift.

  • Scope work that can actually move the metric
  • Decide what not to build
  • Follow up 2–4 weeks after launch and interpret what happened

What Success Looks Like (Year 1)

• Initiative outcomes hit
  • Ship 3–4 initiatives end-to-end
  • At least two clearly move their metric (backed by post-launch review)
• Agent workflow that travels
  • Your prompts, evals, and review loop become reusable patterns adopted by other initiatives
• Faster cycle time
  • Meaningfully reduce median time from problem-framing to first production rollout
• Quality holds
  • No customer- or pro-facing regression traceable to agent-authored code slipping through review
• Visible leverage
  • Peers reference your artifacts—runbooks, evals, agent workflows, and post-launch write-ups

What We’re Looking For

You don’t need every box checked. You do need deep skill in at least one of our stacks and credible production experience shipping with AI coding agents.

• AI-native
  • You ship daily with tools like Claude Code, Cursor, Codex, or equivalents
  • You have strong opinions on prompts, evals, agent loops, and review workflows
  • You know when to let the agent run—and when to write it yourself
• Operating at a lead level
  • Whatever your current title, you’ve consistently been the person making the call, shipping the hard thing, and owning whether it worked
• Outcome-driven
  • You measure your week in “did the metric move” and “did the experience get better”
  • You review dashboards post-launch and own the answer
• A strong horizontal partner
  • You collaborate effectively with PM and design
  • You bring engineering judgment to product calls and product judgment to engineering calls
  • You hold your own with engineering peers in a shared codebase
• Decisive and documented
  • You make architecture/data-model/rollout decisions quickly
  • You write them down, get fast input, and move
• A force multiplier
  • Your impact compounds beyond your initiative through reusable artifacts: agent workflows, evals, runbooks, and post-launch write-ups
• Customer- and pro-minded
  • You care about outcomes for both sides of the marketplace

Good to Know

• Individual contributor role with room to grow. People management is handled by the EM, but management is an open path for those who want it.
• Product engineering, end-to-end: you’ll ship features that move metrics. Platform and architecture work happens within the initiative when the outcome requires it.
• Hands-on with a high quality bar: agents handle much of the implementation; you bring the judgment, safety, design, 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 & observability: AWS, Datadog, Sentry, GitHub Actions
• Documentation & process: Brain (Claude Code skills + docs repo), Confluence, Jira

Benefits

• Competitive base salary: $80,000–$100,000 USD annually
• Work from anywhere (role is remote for candidates located in Belo Horizonte, Brazil)
• High ownership and autonomy
• Fast-moving team that loves to build, learn, and grow

Ready to Ship?

If you’re the kind of engineer who thinks in outcomes, builds safety into workflows, and can lead AI-assisted development without lowering the bar—apply. We’d love to see how you’ve shipped impact in production and how you’ve used AI agents responsibly to move faster.

—