Data Engineer

BEO (formerly Co-Power); München; Vor Ort; EUR 90.000 - 125.000; Vollzeit

Zusammenfassung

BEO (formerly Co-Power) is hiring a Data & ML Engineer to own our data pipelines and bring analytics and optimization models into production. You will operate at the intersection of data engineering, applied ML, and energy systems, collaborating with data scientists and software engineers.

Based in Munich with an office-first approach, you will design scalable real-time and historical processing, ensure data quality, and deploy forecasting and optimization components that directly impact

Qualifikationen

• 4+ years in data/ML engineering or applied data science.
• Strong Python and production-grade code by default.
• Experience building and operating data pipelines over time-series data.
• Strong SQL, PostgreSQL schema design and query optimization.
• Deep understanding of data quality, validation, and monitoring in production.
• Comfortable in an early-stage environment building from scratch.

Aufgaben

• Own and build data pipelines from ingesting time-series telemetry, forecasts, and energy market data to reliable production serving.
• Establish and maintain data quality standards, including validation and anomaly detection.
• Design and evolve data platform architecture for real-time and historical processing.
• Turn forecasting, optimization, and algorithms into robust production systems.
• Collaborate with data scientists and engineers to deploy and run models reliably.
• Integrate data and models into the core product and ensure clean data interfaces with partners.

Kenntnisse

Python

PostgreSQL

SQL

Data pipelines

Time-series data

Production-grade code

Jobbeschreibung

We are hiring a Data & ML Engineer to take ownership of our data pipelines and bring advanced analytics and optimization models into production. This role sits at the intersection of data engineering, applied machine learning, and energy systems, bridging our data science and software engineering efforts.

About BEO

BEO is a new kind of power company: battery-backed and vertically integrated across hardware, software, and financing.

The world is in the middle of an energy transition. We're building out renewables but we're not there yet. Today, electricity is costly and volatile. Industrial prices in Europe have doubled since 2021. That's a €100+ billion disadvantage for European companies. Daily price swings now exceed 500%, so industry can't plan. The scarce resource is no longer generating power. It's storing it. Storage moves power across time.

So we put a battery next to each factory. We finance it all. We run it with our AI-powered optimization engine that buys power when it's cheap, stores it, shaves peak loads, and trades what's left. The customer gets no CapEx, no complexity, just a lower and predictable energy bill. And we don't stop at single sites. Our network runs them as one connected fleet. The more batteries we connect, the more flexibility we pool, and the more value each customer gets.

The 20th century was driven by oil. The 21st will be driven by electricity. We are looking for people who want to build the power company of the future with us.

What you will do

• Own and build our data pipelines, from ingesting large volumes of time-series data (telemetry, forecasts, energy market data) to transforming, validating, and serving them reliably in production
• Establish and maintain strong data quality standards, including validation, anomaly detection, and monitoring
• Design and evolve our data platform architecture for scalable, real-time and historical processing
• Turn forecasting, optimization, and algorithmic ideas into robust, production-ready systems in collaboration with data scientists, and take ownership of deploying and running them reliably under real-world constraints.
• Contribute to forecasting, optimization, and algorithm development, and actively challenge approaches through code reviews, discussions, and hands-on implementation.
• Integrate data and models deeply into our core product in collaboration with engineers.
• Interface with external partners to ensure clean and reliable data integration

What we’re looking for

• 4+ years in data/ML engineering or applied data science
• Strong Python: clean, testable, production-grade code by default
• Solid experience building and operating data pipelines (ETL/ELT) and data models over time-series data, from APIs and batch jobs to scheduled workflows
• Strong SQL, PostgreSQL specifically: schema design and query optimization
• Deep understanding of data quality, validation, and monitoring in production
• Comfortable in an early-stage environment where the platform is built from scratch. You scope pragmatically, make opinionated decisions, and don't wait for perfect requirements

Nice to have:

• Experience in energy markets, industrial systems, or working with hardware-adjacent data
• Background in forecasting, time-series analysis, or operations research

About us:

We are a small team taking on a hard problem, and we hold a high bar. We value ownership, direct and honest communication, and getting better every day. If you like solving complex problems and want to build something big, you'll fit right in. Our office is at Goetheplatz in central Munich. We offer plenty of flexibility but ask for an office-first commitment: when you're not traveling, most of your time is in the office. People learn faster and get more done together.