Staff Software Engineer, Agentic Ads

ABOUT THE ROLE:

Help turn “I built a business” into “I have customers.” As a Staff Software Engineer on Replit’s Money team, you’ll help shape Agentic Ads: an emerging area focused on using AI to make customer acquisition more accessible to businesses built on Replit.

This role focuses on intelligent, advertiser-facing software—not ad-serving infrastructure, an ad exchange, or a real-time bidding engine. You’ll tackle problems at the intersection of AI, business growth, measurement, and trustworthy automation, turning complex decisions into clear, useful experiences.

You’ll help define a new product area, working closely with product, design, and engineering to discover customer needs and deliver practical solutions. This is a hands-on Staff role: you’ll own architecture, lead delivery across teams, mentor engineers, and turn an ambitious vision into incremental customer value.

YOU WILL:

- Set technical direction for Agentic Ads, translating customer needs into an architecture and roadmap that balance rapid learning with long-term reliability.

- Build agent-powered experiences that help businesses make informed growth decisions, translating user goals into understandable recommendations and appropriately authorized actions.

- Design extensible integrations with external services, using well-defined APIs and abstractions that accommodate changing provider capabilities and requirements.

- Partner with product and data teams to establish reliable measurement, connect product activity to business outcomes, and address data quality, delayed feedback, and uncertainty.

- Develop intelligent automation that learns from performance signals and helps users improve outcomes within their goals and constraints.

- Make financial control a product requirement: scoped authorization, explicit approvals, budget limits, auditable decisions, clear reporting, and reliable pause controls. Distinguish recommendations from actions that commit customer spend.

- Make cross-platform workflows reliable with durable state, idempotency, safe retries, reconciliation, observability, and recovery from partial failures, expired credentials, rate limits, and provider API changes.

- Establish agent evaluations and production monitoring for plan quality, tool selection, policy compliance, spend safety, and verified execution. Partner on experiments that distinguish attributed results from incremental customer value.

- Lead ambiguous initiatives across product, design, AI, data, security, and partnerships. Stay hands-on with implementation, define incremental milestones, mentor engineers, and own the quality and operation of what the team ships.

REQUIRED SKILLS AND EXPERIENCE:

- A track record of Staff-level technical leadership on complex customer-facing products or platforms: setting direction, resolving ambiguity, and delivering through launch and production operation across multiple teams.

- Strong hands-on software engineering and system design skills across APIs, data modeling, distributed systems, asynchronous workflows, and customer-facing product experiences.

- Experience building and operating third-party integrations that remain correct under duplicate requests, partial failures, rate limits, changing schemas, and inconsistent external state.

- Practical experience shipping LLM-powered products or agentic workflows, including tool use, orchestration, evaluations, and safeguards for actions taken against external systems.

- Strong data and measurement judgment: experience using instrumentation and experiments to evaluate product outcomes, and the ability to reason about noisy data, delayed feedback, uncertainty, and correlation versus causation.

- Sound judgment around systems that act on a user’s behalf, including authentication, authorization, sensitive data, approval boundaries, and limits on consequential actions.

- Demonstrated ability to align cross-functional teams, explain technical trade-offs, mentor engineers, and drive execution without relying on reporting authority.

- A product-minded approach to simplifying complex workflows for non-experts, with hands-on ownership from prototype through reliable production operation.

PREFERRED QUALIFICATIONS

- Experience building advertiser-facing products, marketing automation, campaign-management tools, growth platforms, or software that helps businesses acquire customers.

- Experience integrating advertising or marketing APIs; familiarity with account onboarding, campaign lifecycles, and platform requirements.

- Working knowledge of conversion tracking, attribution, customer acquisition cost, return on ad spend, budget pacing, and the limits of optimizing with low conversion volume.

- Experience with experimentation, incrementality measurement, constrained optimization, recommendation systems, or decision-making under uncertainty.

- Experience building permissioned, multi-tenant products with approval workflows, budget controls, audit trails, and privacy-aware handling of customer and conversion data.

BONUS POINTS:

- Experience with agent tooling, durable workflow execution, delegated authorization, or evaluation frameworks for agents that take consequential actions.

- Experience connecting application events or server-side conversion signals to advertising platforms, or integrating creative generation and landing-page experimentation into growth workflows.

- Experience building for small businesses or first-time advertisers, where clear guidance, limited budgets, and sparse data shape the product.

- These are additional strengths, not a checklist. Experience with every ad platform is not expected; ad-serving infrastructure experience and an ML research background are not prerequisites.

WHAT WE VALUE:

- Customer outcomes: success means helping a business acquire qualified leads and customers—not merely connecting an account, launching a campaign, or increasing spend.

- User control and trust: agents explain recommendations, act within explicit authority, and make budgets, costs, and consequential changes understandable.

- Evidence over activity: we validate measurement, acknowledge uncertainty, and test whether a change improves business outcomes rather than treating attribution as proof of causality.

- End-to-end ownership: we own the journey from a business goal through campaign execution, measurement, and ongoing improvement.

- Pragmatic technical leadership: we build on existing ad platforms, ship focused increments, and invest in correctness and extensibility where they matter.

- Clear collaboration: we document decisions, surface risks early, and help other teams and partners succeed.