---
title: 'Software Engineer, Agent Platform at Retool'
canonical: 'https://feeny.ai/job/software-engineer-agent-platform-retool-san-francisco-rhdp6pt05hmt'
type: 'job'
last_seen: '2026-09-24'
---

# Software Engineer, Agent Platform at Retool

- **Company:** Retool
- **Location:** San Francisco, CA
- **Compensation:** $164k–$306k
- **Employment:** full-time
- **Work type:** hybrid
- **Posted:** 2026-09-18
- **Last confirmed live:** 2026-09-24
- **Apply:** https://jobs.gem.com/retool/am9icG9zdDrWsqKmo7GEKkxG6frVxgV7

## Job description

## WHY WE’RE LOOKING FOR YOU

We’re building AI-native products where model behavior is part of the product, not just an implementation detail. As LLMs become more capable, the bottleneck is no longer access to models—it’s making non-deterministic systems reliable, evaluable, and trustworthy in production.

We’re hiring AI Engineers to own that problem end to end. This is not a role for someone who simply integrates AI APIs into features. It’s for engineers who take responsibility for how probabilistic systems behave over time, how quality is measured in the presence of variance, and how capabilities improve without regressing.

If model regressions, subtle behavior drift, or edge-case failures keep you up at night—and you enjoy that kind of ownership—we want to talk.

## WHAT YOU’LL DO

As an AI Engineer, you’ll own model-driven behavior in production systems, working across product, infrastructure, and evaluation layers. Your work will directly shape what users experience—and how confidently the team can ship. You might:

- Own the behavior of AI-powered features across multiple product surfaces, including quality, safety, variance, and failure modes
- Design and evolve prompting, retrieval, routing, and tool-use strategies that embrace non-determinism while bounding its downside
- Build and maintain evaluation systems that measure model performance using statistical signals, distributions, and trends—not just pass/fail tests
- Detect, diagnose, and resolve non-deterministic failures such as hallucinations, partial correctness, instruction drift, or sensitivity to context changes
- Define and implement guardrails, fallbacks, and degradation paths that keep systems useful even when models behave unexpectedly
- Partner with product and infra teams to decide when probabilistic behavior is “good enough” to ship—and when it isn’t
- Influence model selection, model behavior, and tool design to balance quality, cost, latency, and robustness for real user workflows

You’ll work across the stack (e.g., TypeScript, Node.js, React), but your leverage won’t come from code volume alone—it will come from shaping runtime behavior with precision, measurement, and intent.

## WHAT THIS ROLE IS (AND IS NOT)

This role is:

- Accountable for AI behavior, not just system correctness
- Grounded in evaluation, iteration, and regression prevention under non-determinism
- Comfortable designing systems where outputs vary, confidence is probabilistic, and correctness is contextual
- Focused on shipping dependable products on top of imperfect components

This role is not:

- Adding LLM calls to existing features and moving on
- Treating models as black boxes with undefined behavior
- Shipping AI features without owning their long-term reliability, drift, or user trust

## THE SKILLSET YOU’LL BRING

- 6+ years of professional engineering experience, with ownership over complex systems in production
- Demonstrated experience owning AI/LLM behavior beyond basic integration, including mitigation of variance and failure modes
- Comfort reasoning about probabilistic systems and tradeoffs (quality vs. cost, recall vs. precision, speed vs. robustness)
- Experience designing or maintaining evaluation frameworks, golden datasets, regression detection, or human-in-the-loop feedback loops
- Strong product intuition—you care deeply about what “good” looks like even when outputs are non-deterministic
- Ability to operate independently in ambiguous problem spaces and set quality standards others rely on
- Strong opinions, weakly held—you iterate quickly and adjust based on evidence and observed runtime behavior

## BONUS POINTS

- Experience with RAG, agentic systems, or tool-using models in production
- Familiarity with vector databases, embeddings, or retrieval pipelines
- Exposure to fine-tuning, model routing, or post-training techniques
- Experience building shared AI infrastructure used by multiple teams
- History of mentoring engineers on designing for non-determinism and evaluation-driven development

## WHO YOU’LL WORK WITH

You’ll join a small, senior team focused on advancing AI capabilities across the product. You’ll collaborate closely with product engineers, infra engineers, designers, and PMs—often acting as the final owner of AI behavior and quality before features reach users.

Your work will set standards that others build on. If you enjoy being the person teams rely on when AI behavior matters most—and certainty is never guaranteed—you’ll thrive here.

READY TO BUILD RELIABLE AI SYSTEMS?

If you’re excited to move beyond demos and take real ownership of non-deterministic behavior in production—defining quality, preventing regressions, and turning variability into a strength—we’d love to meet you.

## About Retool

## Company Overview
- **One-liner**: Retool provides a platform for building, deploying, and managing custom internal software and AI applications by connecting to any database, API, or LLM.
- **Entity Type**: Private (Series C)
- **Headquarters**: San Francisco, California, United States
- **Founded**: 2017
- **Founders**: David Hsu (CEO)

## Core Business
- **Primary industry**: Software Development, Enterprise Internal Tools, AI Application Platform
- **Target customers**: B2B, Enterprise, SMB; specifically developers, IT teams, and business operators building internal software
- **Mission or purpose**: To enable companies to build production-ready internal software and AI applications dramatically faster, with enterprise-grade security and governance, so that domain experts and developers alike can solve critical business problems.

## Products & Services
- **Retool App Builder**: A low-code platform to build custom internal apps (dashboards, admin panels, CRUD tools) by connecting to databases and APIs. Type: SaaS/Platform.
- **Retool Workflows**: A visual automation tool to build and orchestrate complex business processes and backend logic. Type: SaaS/Platform.
- **Retool AI**: An AI-powered app generation capability that transforms natural language into production-ready applications, agents, and workflows, integrating with any LLM. Type: AI Feature/Platform.
- **Retool Mobile**: A solution to build and deploy internal mobile apps from the same Retool platform. Type: SaaS/Platform.

## Market Standing
- **Valuation/Market Cap**: Not publicly disclosed (last round was Series C).
- **Key Metric**: Annual Revenue of $5 million (as per LinkedIn company data); Total Funding of $141.3 million.
- **Notable Investors/Partners**: Sequoia Capital (lead), Nat Friedman, John Collison, Daniel Gross. Customers include Amazon, Stripe, Brex, and Orangetheory Fitness.
- **Growth Signals**: Over 10,000 organizations use Retool. The company has automated over 100 million hours of work. It has 6 offices across the US and UK. Despite a recent headcount reduction (-11% YoY), it maintains a strong brand in the enterprise internal tools space and is aggressively pivoting into AI-powered app generation.

## Competitive Advantages
- **Enterprise Governance from Day One**: Unlike point solutions, apps built in Retool are production-ready and pass security reviews, eliminating the need for rebuilds or audit scrambles.
- **Deep Data Connectivity**: Securely connects to existing databases, APIs, and internal systems, ensuring apps run on real data with real permissions.
- **Unified Platform**: One platform to manage, orchestrate, and scale all internal apps, agents, and workflows, providing centralized visibility and governance for IT.
- **Trusted by Large Enterprises**: A strong customer base of high-profile companies (Amazon, Stripe, Brex) serves as a powerful validation of its enterprise readiness.

## Strategic Focus
- **AI as the Core Platform**: Retool is positioning itself as the "first enterprise AppGen platform," where AI is used to generate production-ready code from natural language, expanding the definition of "developer" to include analysts and operators.
- **Scaling Enterprise Features**: The company is focused on building out governance, security, and platform capabilities to support large-scale deployments across complex organizations.
- **International Expansion**: With offices in London and a German-speaking Sales Engineer role, Retool is actively expanding its presence in the European market.

## Why Work Here
- **Culture**: The company values ambition, intense curiosity, energy, and deep care. They emphasize moving fast, acting like an owner, and being both demanding and supportive.
- **Work Environment**: Hybrid model with offices in San Francisco, New York, Salt Lake City, and London. The company believes great work happens when teams collaborate in person.
- **Product Impact**: Employees are close to the product and use Retool internally, giving them a direct voice in improving it. The mission is to enable a wider community of builders to create production-grade software safely.
- **Hiring Process**: Structured, with initial recruiter/hiring manager chats, a technical evaluation or practical exercise, and a final round of 3–5 interviews. The company aims for transparency and candidate preparation.
- **Employee Sentiment**: Employer rating of 3.4/5.0 (127 reviews). Strengths include Work-Life Balance (4.1) and Culture (3.7). Compensation (3.4) and Career (3.4) are areas for potential improvement.

## Sources
1. [retool.com](https://retool.com/)
2. [retool.com/careers](https://retool.com/careers)
3. [retool.com/about](https://retool.com/about)
4. [linkedin.com/company/tryretool](https://www.linkedin.com/company/tryretool)
5. [jobs.gem.com/retool](https://jobs.gem.com/retool)

## Other roles at Retool

- [Software Engineer, Sandbox & Agent Executor](https://feeny.ai/job/software-engineer-sandbox-agent-executor-retool-san-francisco-ftyfs2tqw2gt) — San Francisco, CA
- [Software Engineer, Automations](https://feeny.ai/job/software-engineer-automations-retool-san-francisco-c5mkacjvq8zh) — San Francisco, CA
- [Product Manager, Integration Platform & Partnerships](https://feeny.ai/job/product-manager-integration-platform-partnerships-retool-san-francisco-gbw4m402pqcn) — San Francisco, CA
- [Product Manager, AI Platform Infrastructure](https://feeny.ai/job/product-manager-ai-platform-infrastructure-retool-san-francisco-7hehw89e4nez) — San Francisco, CA
- [Staff Copywriter](https://feeny.ai/job/staff-copywriter-retool-united-states-wraskj0df9as) — United States
- [Software Engineer, Enterprise Expansion](https://feeny.ai/job/software-engineer-enterprise-expansion-retool-san-francisco-y20tg7mpkr2z) — San Francisco, CA
- [Senior Manager, Events & Field Marketing](https://feeny.ai/job/senior-manager-events-field-marketing-retool-united-states-tqdp9jzev9ms) — United States
- [UX Research Manager](https://feeny.ai/job/ux-research-manager-retool-san-francisco-fsj427an79p5) — San Francisco, CA
- [Enterprise Account Executive, EMEA](https://feeny.ai/job/enterprise-account-executive-emea-retool-london-ppnz3v0ba101) — London, United Kingdom
- [Site Reliability Engineer (SRE)](https://feeny.ai/job/site-reliability-engineer-sre-retool-san-francisco-8dfvm4014zmx) — San Francisco, CA