We're building AI agents for performance marketing.

Plurio is the AI agent for media buying teams running $300K–$15M/month on Google, Meta, and TikTok. It connects to your internal backend data and your ad accounts, automates analysis and optimization, saves 50% of time, and boosts ROAS by 10–30%. Watch a five-minute demo.

Plurio transforms how media buying teams work:

1. From manually analyzing dashboards → to the AI agent doing deep data research in minutes.

2. From manually adjusting budget → to the agent suggesting optimal split at channel, campaign, and ad-set level.

3. From manually killing / scaling / relaunching creatives → to agents autonomously performing those actions in ad platforms, based on full-funnel data.

4. From decisions made with gut feeling → to agents optimizing automation rules with historical data and ML models.

Our agents already run $500M+/year in ad spend (see this inside a $20M+/year UA team). Since our public release in March, our customer base has grown 5×.

Our goal, and the mission we'd build together, is the autonomous user acquisition factory that runs 10× better than anything that came before, growing budgets under management to $30B/year.

The Role

You own forecasting in Plurio: the conversion and LTV forecasts our clients' ad budgets are optimized against.

In most of our clients' funnels the money doesn't arrive on day one. A user installs, registers, places a first order, comes back for a second, renews a subscription weeks later. Ad platforms can't wait that long to learn, so they need an early, honest estimate of what each user is worth. Your forecasts are that estimate. If they're accurate, budgets flow to the campaigns that actually pay back. If they're biased, money goes to the wrong place at scale.

What You'll Own

Building forecasts Forecast conversions and LTV from a user's first events and update them as new data arrives. Your inputs are the client's own data, ad-platform data, and our attribution.

Choosing the right method Statistics, ML, or LLM-based approaches: whatever beats the baseline forecast on the client's data. No favorite models.

One solution, many clients Build a reusable solution that launches quickly for a new client, then tune it to that client's funnel and data.

Measuring accuracy Backtesting on historical data and validation on a time-based holdout; error and bias by horizon and by segment; calibration. You develop the methodology for evaluating forecast quality and keep tracking it in production.

You're the Right Person If

Requirements:

— Production forecasting models with measurable impact. You've launched LTV, conversion, or churn models that the business relied on.
— Strong SQL and Python. We barely write code by hand — AI does the heavy lifting. Your job is to make sure it's correct.
— You can explain it to the business. You tell a marketer in plain words how accurate a forecast is and what it depends on.
— You work with AI every day and build with it, not just chat with it.
— Professional-level English: you'll communicate directly with client teams.

⚡️ It'd Be a Plus If

• Experience in marketing: performance marketing, user acquisition, attribution.

• ClickHouse, dbt.

What You Can Expect

• Competitive compensation, aligned with senior data-science experience; specifics discussed individually.

• AI-first culture, for real: the whole company works in Cursor with a shared workspace and premium team access to AI tools. You'll have the best agentic tooling in the industry and a team that expects you to use it.

• Maximum impact: your models go live in client accounts, not into slide decks. No corporate bureaucracy between you and the result.

Hiring Process

1. Application: CV + short answers (see below). We aim to respond within 48 hours.

2. Intro call (People & Operations, ~30 min): company overview, background, motivation, logistics.

3. Take-home assignment: a forecasting task to solve on your own.

4. Technical interview: a deep dive on conversion and LTV forecasting in a real scenario.

5. Paid trial period: a short stint of real work.

6. Offer: if it's a fit, we align on terms and start date.

How to Apply

Click "Apply for this role" and fill in the form: your CV, LinkedIn, and a few questions about the performance and UA roles you've closed.