> Markdown version of [/jobs/ext/3095747-staff-software-engineer](https://www.wearedevelopers.com/jobs/ext/3095747-staff-software-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Staff Software Engineer - **Company:** Replit, Inc. - **Location:** United States - **Contract:** Permanent contract - **Skills:** Application Programming Interfaces (APIs), Artificial Intelligence, Audit Trail, Distributed Systems, Machine Learning, Automation of Marketing, Recommender Systems, Conversion Tracking, Software Engineering, Large Language Models, Adserver - **Published:** September 26, 2026 - **Apply:** https://startup.jobs/staff-software-engineer-agentic-ads-replit-3-10202175 ## About the Role * 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., * 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. ## Description 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., * 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. ## Related Videos - [ Your Code Is the Sales Team Now](https://www.wearedevelopers.com/videos/100327-your-code-is-the-sales-team-now) - [Resilient by Design: Building Robust Architectures in High-Stakes Financial Systems](https://www.wearedevelopers.com/videos/2106-resilient-by-design-building-robust-architectures-in-high-stakes-financial-systems) - [Introduction to Azure Machine Learning](https://www.wearedevelopers.com/videos/368-introduction-to-azure-machine-learning) - [Agentic employees in world's most downloaded FinTech app](https://www.wearedevelopers.com/videos/100123-agentic-employees-in-world-s-most-downloaded-fintech-app) - [No Keys for the Robot: GitOps as the Control Plane for Autonomous Agents](https://www.wearedevelopers.com/videos/100095-no-keys-for-the-robot-gitops-as-the-control-plane-for-autonomous-agents) - [What non-automotive Machine Learning projects can learn from automotive Machine Learning projects](https://www.wearedevelopers.com/videos/397-what-non-automotive-machine-learning-projects-can-learn-from-automotive-machine-learning-projects) ## Related Articles - [Dev Digest 120 - Apple and peers](https://www.wearedevelopers.com/magazine/455-dev-digest-120-apple-and-peers) - [Why Upskilling And Reskilling is Important For Developers](https://www.wearedevelopers.com/magazine/428-why-upskilling-and-reskilling-is-important-for-developers) - [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift) - [How to Answer the Interview Question: “Why Do You Want to Be a Software Engineer?”](https://www.wearedevelopers.com/magazine/392-how-to-answer-the-interview-question-why-do-you-want-to-be-a-software-engineer) - [Is Software Engineering Over-Saturated?](https://www.wearedevelopers.com/magazine/418-is-software-engineering-over-saturated) - [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline)