Save Job
Posted 6mo ago

Software Engineer, Full-Stack

@ Marlo
San Francisco, California, United States
$140k-$200k/yrOnsiteFull Time
Responsibilities:Scale intelligence, Engineer workflows, Build feedback loops
Requirements Summary:3+ years professional experience; backend-focused with AI systems; in-person in San Francisco; strong ownership and product intuition.
Technical Tools Mentioned:Temporal, BullMQ, Celery, Gmail APIs, LLM tooling
Save
Mark Applied
Hide Job
Report & Hide
Job Description

Overview

Marlo is the intelligence layer for the creator economy. We are building an agentic operating system that moves beyond simple organization to live deal execution. By bridging unstructured communication with deep industry context, Marlo acts as an autonomous teammate for the world’s most ambitious talent agencies.

We’ve spent the last few months deploying in-production with elite agencies, proving that the future of media won't be run on email threads and spreadsheets, but on high-reliability AI systems.

Role

We’re looking for an engineer to build the core systems powering the future of creator work. This is a full-stack role with a backend tilt, where you’ll own systems end-to-end—from durable Gmail ingestion pipelines to LLM-based decision engines.

In this role, you will:

  • Scale the intelligence layer: Partner with the CTO to evolve our backend architecture to a stateful, proprietary representation of the talent ecosystem

  • Engineer agentic workflows: Architect resilient, multi-step AI agents that can navigate complex brand negotiations using reasoning, tool-use, and multi-step decision-making

  • Build self-learning feedback loops: Design infrastructure to capture human-in-the-loop signals, turning every user interaction into data that improves our model performance

  • Solve tough integration problems: Architect robust, fault-tolerant consumers for the volatile APIs (Google, TikTok, IG) that serve as our primary data streams

Requirements

  • 3+ years of professional experience, ideally in high-growth or early-stage environments

  • Deeply comfortable with resilient backend architecture. You’ve used asynchronous workflows (Temporal, BullMQ, Celery) and understand failure modes, retry logic, and observability at scale

  • Experience engineering AI systems: You understand the trade-offs between long-context windows, RAG, and structured graphs to deliver high-accuracy context at low latency

  • Strong product intuition. You think in terms of underlying data structures and how they solve user problems

  • Radical ownership. You see a problem and feel compelled to solve it to help the team move faster

  • In-person in San Francisco: We believe in high-bandwidth collaboration and building software with soul

Get in touch: [email protected]