Staff Software Engineer, Product (Mexico City)

Staff Software Engineer, Product (Mexico City)

Own the outcome. Lead an initiative end-to-end. Build with AI agents—without compromising on quality. If you’re the kind of engineer who thrives on shipping to a real marketplace and making the hard calls (architecture, safety, rollout, and measurement), this is your next move.

This is a remote role for candidates located in Mexico City, Mexico.

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—powered by a single shared platform across three brands:

• LawnStarter
• Lawn Love
• Home Gnome

About Engineering at LawnStarter

We build in small, focused initiative teams. Each team is anchored by 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 inside a shared codebase. The whole team owns whether the work moves the metric.

AI coding agents are a force multiplier for us: they help small, senior teams ship more, faster, and at a higher bar for quality. We hire engineers who are wired for ownership and energized by delivering to customers and pros—both sides of the marketplace.

About The Role

As a Staff Software Engineer, Product, you’ll be the engineering anchor of an initiative. You’ll work in a tight loop with your PM and designer, and you’ll partner with engineering peers across initiatives.

You’ll own the full lifecycle:

• Framing the problem and shaping the technical approach
• Directing AI agents to implement much of the code
• Handling sensitive areas where careful, hand-written code is required
• Shipping to production
• Owning the outcome with your team—measured by impact, not output volume

How you’re measured: by impact. We don’t optimize for lines of code. When an agent can ship safely, your job is to ensure it’s done right and that the initiative’s metric moves. When the area is sensitive, you write the code yourself.

What You’ll Do

• Ship end-to-end—from problem framing through production and post-launch metric review
• Partner deeply with product—bring engineering judgment to product decisions and product sense to engineering decisions
• Operate with autonomy—make most technical calls yourself, with architect review on major architectural decisions and quick peer input to pressure-test your thinking
• Build agent workflows that hold the bar—prompts, guardrails, evals, tests, and review loops that let agents deliver safe, production-ready code
• Own initiative architecture—technical approach, data model, integrations, rollout plan, observability, and rollback strategy
• Ensure quality at staff level—production correctness, security, performance, observability, and customer/pro experience
• Measure what matters—follow the metric, decide what to build (and what not to build), and evaluate results 2–4 weeks after launch

What You’ll Own

• The technical approach: architecture, data model, integration choices, rollout plan, observability, and rollback strategy for your initiative
  • Most decisions are yours
  • Major architectural calls go to architect review
  • You document decisions and revisit if the data proves you wrong
• Implementation quality: prompts, guardrails, evals, tests, and a review loop that enables agents to ship safely
  • Most code will be agent-authored
  • You remain accountable for correctness and quality—same standard as the rest of the team
• Cross-functional partnership:
  • Daily working contact with your PM (scope and tradeoffs)
  • Collaboration with your designer (UX decisions and in-tool prototyping)
  • Regular collaboration with engineering peers
  • Weekly check-ins with your Engineering Manager
• The initiative outcome:
  • With your PM, present results 2–4 weeks post-launch
  • Share the real “did it work?” answer
• A high bar for what ships—agents accelerate delivery; they don’t reduce standards

Problems You’ll Solve

• Lead AI agents at a staff-level quality bar
  • Make agents ship like a senior engineer wrote it
  • Encode conventions in prompts
  • Use evals to catch issues before merge
  • Write tests that hit edge cases
  • Build observability that detects regressions before customers feel them
  • Design a workflow that lets a small senior team ship far beyond its size
• Own high-autonomy decisions
  • Move quickly with latitude for engineering calls
  • Get architect review on the biggest architecture decisions
  • Pressure-test thinking with peers
  • Keep the team aligned and accountable to outcomes
• Ship outcomes, not features
  • Each initiative is measured by a metric (conversion, retention, pro-funnel KPI, unit economics, etc.)
  • You’re accountable for the number alongside your team
  • Scope with discipline: decide what not to build
  • Follow up 2–4 weeks post-launch to learn what actually 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 travels:
  • Your prompts, evals, and review loop are adopted by peers across other initiatives
• Faster cycle time:
  • Meaningfully shorter median time from problem-framing to first production rollout
• 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 using tools like Claude Code, Cursor, Codex, or equivalents
  • You have strong opinions about 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:
  • Even if your title isn’t “Staff” today, you’ve been the person making the calls, shipping the hard work, and standing behind the outcome
• Outcome-driven:
  • You measure your week by whether the metric moved and whether the experience improved
  • You read post-launch dashboards and own the answer
• A strong horizontal partner:
  • You collaborate well with PMs and designers
  • You bring engineering judgment to product calls and product judgment to engineering calls
  • You can hold your own with peers across a shared codebase
• Decisive and documented:
  • You make architecture, data-model, and rollout decisions quickly
  • You document them, get fast input, and move
• A force multiplier:
  • Your impact compounds beyond your initiative
  • You leave reusable artifacts—agent workflows, evals, runbooks, post-launch reviews
• Customer- and pro-minded:
  • This is a real marketplace with real people on both sides
  • You care about outcomes for customers and pros

Good to Know

• Individual contributor with room to grow:
  • People management is handled by your EM
  • But the path into management is open for those who want it
• Product engineering, end-to-end:
  • You ship features that move metrics
  • Platform and architecture work can happen inside the initiative when needed
• Hands-on with a high quality bar:
  • Agents handle much of the implementation
  • You bring judgment, safety, and accountability—and the bar is high
• 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

You don’t need every box checked. We’re looking for deep skill in at least one of our stacks plus credible production experience shipping with AI coding agents.

Benefits

• Competitive compensation: USD $80,000–$100,000 annual base
• Work from anywhere (remote; Mexico City location required)
• High ownership and autonomy
• Fast-moving team that loves building, learning, and growing