ML Quantitative Researcher

Overview

This role involves designing predictive signals at the core of live systematic equity investment strategies where the research conducted directly impacts the trading outcomes. The position is with a quantitative asset management firm based in Germany that focuses on equity strategies as well as asset allocation across developed markets.

Role Description

You will be joining a dedicated research group that develops machine learning models to rank stocks by their expected relative returns. Ownership of the signals that feed these models will be a primary responsibility. This is a hands-on position where the signals are integral to actual trades rather than auxiliary analysis tools. The team values both the economic rationale and empirical validation of each signal.

Key Responsibilities

• Explore various datasets and investment universes to identify predictive signals with sustainable out-of-sample performance, considering both statistical robustness and sound economic reasoning.
• Transform raw, complex data inputs such as prices, trading volumes, fundamental company data, and text into reliable, well-tested, and configurable signal components using rigorous point-in-time principles.
• Aggregate clusters of correlated signals into a limited set of robust composite signals per universe, ensuring weighting prioritizes originality and informativeness while removing biases caused by drift.
• Establish automated research workflows using agentic and large language model (LLM) technologies to generate ideas, perform parameter sweeps, and produce automated evaluation reports.

Candidate Qualifications

• Advanced degree (Master's or PhD) in a quantitative field such as mathematics, physics, computer science, financial engineering, statistics, or a relevant equivalent.
• Strong grounding in statistics and econometrics, coupled with the ability to maintain composure when working with noisy, real-world data.
• Experience writing production-level Python code collaboratively, including use of version control, code reviews, and writing clean, extensively tested code. Familiarity with testing frameworks like pytest and data validation libraries like Pydantic is important.
• Proficiency in modern dataframe libraries such as Polars or pandas for efficient data manipulation.