Public summary
Join a Berlin-based quantitative asset manager focused on systematic equity and asset allocation strategies. Work within the Equity Selection team to develop, evaluate, and implement alpha signals that drive machine-learning stock return forecasts. Collaborate in an interdisciplinary environment that combines quantitative finance, software engineering, and machine learning, contributing directly to live investment strategies.
Location and work setup
- Location
- Berlin
- Remote status
- On-site
- German requirement signal
- No German Required Detected
- Detected job language
- English
Responsibilities
Build and evaluate individual alpha signals across datasets and investment universes, assessing their statistical and economic performance. Transform raw data (prices, volumes, fundamentals, text) into robust alpha signals as parameterised components within a feature computation graph while avoiding look-ahead bias. Combine correlated signals into composite robust signals weighted by uniqueness and information content. Automate the research workflow through development and use of large language model and agentic tooling to discover signals, run experiments, and generate reports.
Qualifications
Master's degree or PhD in mathematics, physics, computer science, financial engineering, statistics, or a related quantitative field. Strong foundation in statistics and econometrics with practical experience interpreting noisy real-world data. Proficiency in Python development, including collaborative tools such as Git and code review. Ability to write maintainable, well-tested code using frameworks like Pydantic and pytest. Experience with data manipulation libraries like Polars or pandas. Interest in financial markets and quantitative investment processes. Preferred: experience in alpha signal identification and evaluation for equity strategies, familiarity with ML frameworks (scikit-learn, LightGBM, PyTorch), experience building LLM/agentic tools, and knowledge of numerical/statistical libraries such as SciPy, statsmodels, and MLflow.