SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Nomos is building a full-stack power company to unlock flexibility in Europe's energy markets by connecting millions of homes to grid infrastructure. The company aims to address Europe's electricity cost disadvantage versus the US and Asia by enabling solar adoption and market participation at scale.
In this Research role, you will develop quantitative models and systems that drive real operational and financial decisions across Nomos's energy portfolio. Your work will span three core areas:
**Core Responsibilities:**
- Build forecasting models that predict electricity consumption and generation patterns across the customer portfolio, accounting for dynamic customer behavior and information asymmetries.
- Design and execute procurement strategy for electricity markets, managing downside risk from rare but high-impact price spike events.
- Optimize the real-time steering of thousands of distributed assets (batteries, heat pumps, solar installations) against market prices, forecasts, and physical constraints.
**Key Challenges:**
- Forecast a system that reacts to your models: customers with batteries or heat pumps have information advantages and will respond strategically to price signals. Your models must predict individual behavior before it occurs.
- Price extreme tail events: a handful of hours can define much of the year's financial downside, but historical data on such events is sparse. Build resilient models that don't overfit to past shocks.
- Translate valid ideas into production systems: move from research to reliable, real-world deployment while maintaining accountability for live performance.
**About the Team:**
Nomos has assembled an exceptional team including IMO and IOI medalists, former founders, and Olympic athletes. The company is backed by Index Ventures and is positioned to become a European category leader in one of the world's largest industries.
**Requirements:**
- Ability to defend modeling choices: explain your approach, why you chose it over alternatives, and which observations would invalidate your results.
- Strong data hygiene and skepticism: identify data leakage, weak validation practices, overtesting, and assumptions that would not hold in live deployment.
- Hands-on execution: turn ideas into reliable systems, work with messy real-world data, and take responsibility for model performance in production.
- Curiosity and genuine excitement about energy markets, grid optimization, and climate impact. The posting explicitly welcomes applicants unsure they meet all criteria.
