Senior Data Engineer (Generalist, AI-native)

Job Description

• Full-Time
• Remote
• 5.000 - 7.000 USD

Job description

About the company

We are an AI-powered platform that helps corporate event planners find private dining venues for business events across major U.S. cities. Our core asset is data: we discover, vet and enrich hundreds of thousands of restaurants, bars and hotels, down to the specific private rooms inside each venue.

The role

We’re looking for a generalist data engineer who thinks like a scientist. You’ll own our biggest challenge: data collection and data quality across the whole venue pipeline, from automated discovery and scraping to the human-in-the-loop research process.

This is not an infrastructure-heavy role, and it’s not a dashboards-and-analytics role. Our infrastructure is simple and our pipelines already work. What we need is a fresh, critical eye: someone who understands what we’ve built, finds what’s wrong with it, tests alternatives and proves with data what makes it better.

We use coding agents for almost everything. That’s exactly why we don’t want someone who passes our instructions to an LLM and hands back whatever it produces. We want someone who interprets the problem, prompts thoughtfully, checks the data, questions the results and holds the output to a high bar.

What you’ll do

• Diagnose data quality issues across our venue pipeline: discovery, vetting, scraping and enrichment (duplicates, missing fields, wrong mappings, inconsistent formats).
• Form hypotheses, run experiments and evals, and present before-and-after results backed by data.
• Improve existing pipelines and rebuild parts of them where it makes sense, while keeping their entry and exit points intact.
• Design LLM-based extraction and enrichment from text and images, with traceability and validation built in.
• Ingest data from APIs and web sources, and maintain our dbt models and Dagster workflows.
• Shape how our automation works alongside the research team, and learn from their work to automate more of the process.

What success looks like

Within your first week, you’ll take a real problem in our system and come back with: what you found, your hypothesis for fixing it, the experiments and evals you ran, and the before-and-after results. We can teach you our infrastructure in half an hour; the thinking is what we’re hiring for.

What we’re looking for

Must-haves

• Excellent written and spoken English, and the ability to explain your work clearly and concisely: high signal, no rambling.
• A critical eye: you check the data, question what the LLM gives you and iterate on your own, without needing to be guided.
• Genuine curiosity about hard, messy data problems, and the habit of reasoning from first principles when the problem is new to you.
• 4+ years of data engineering experience, including dbt and the modern data stack.
• At least 12 months with coding agents (Claude Code, Codex or similar) as your main way of working.
• Experience working with English-speaking international teams, ideally 2+ years with US companies.

Nice to have

• Web scraping experience.
• LLM-based enrichment workflows that keep data traceable and valid.
• Running evals and experiments to compare approaches.
• Dagster or a similar orchestration tool.
• Some experience with DevOps, CI/CD and database management.

How we work

We’re mostly async. We talk on Slack throughout the day and have about four planned syncs a week, plus ad hoc calls when needed. You’ll work US hours and report directly to our technical co-founder.

• Full-time contractor position, 100% remote.
• High ownership of the codebase and the product.

Hiring process

1. Screening call with Company’s technical co-founder.
2. Timed take-home challenge (3 hours, started whenever you’re ready).
3. One-hour walkthrough of your solution and thought process.
4. Conversation with the other co-founders.