Quantitative Researcher Equity Statistical Arbitrage

As a Quantitative Researcher within the Equity Statistical Arbitrage wing you will spearhead a data-centric workflow to capture alpha by elevating predictive modeling standards to the highest levels. This role focuses on creating a world-class modeling workflow that transforms massive financial datasets into mathematical models with a specific emphasis on uncovering untapped signals within the fixed-income section of the traded universe. You will tackle complex software infrastructure challenges including the optimization of calibration frameworks the implementation of robust data preparation pipelines and the prototyping of novel time-series architectures. Operating in a high-autonomy environment with short feedback cycles you will bridge the gap between advanced machine learning and market microstructure to build scalable risk-managed portfolios. The ideal candidate possesses at least three years of professional experience and demonstrates a scientific inquisitive mind that balances theoretical depth with practical implementation. You should be highly proficient in mathematics statistics and the full machine learning stack from data generation through to real-life validation. Strong programming skills in Python for data wrangling and numerical programming are essential as this is a development-heavy role requiring evidence of real-world application rather than a purely academic focus. While a PhD from a top-tier university is preferred we value candidates from physics engineering or computer science backgrounds who have experience in the valuation and hedging of fixed-income instruments. Success in this position requires the ability to engage on a nitty-gritty technical level while driving change across the broader modeling strategy.

About the Team

The Quant team consists of eighteen passionate quantitative researchers covering 6 nationalities with thirteen PhDs and five MScs with expertise in statistical analysis mathematical modelling and machine learning. The stat-arb sub-team is a tight group of 3 researchers.

We enjoy collaboration and are always willing to lend a helping hand. We work alongside a team of software engineers and a team of traders that implement and conceive the mathematical models together with us. All team members across the organization write code and drive change and are equally willing to engage on a nitty-gritty technical level as well as discuss the larger strategic level.

The Role

We are seeking a Quantitative Researcher to join the Equity Statistical Arbitrage wing of Alipes Capital. This position is focused on:

• Elevating our predictive modelling standards to the highest levels in the area of statistical arbitrage of traded funds.
• Creating a world class modelling workflow enabling the team to turn massive data sets of financial information into mathematical models that accurately predict movements in the markets.
• In particular the fixed-income section of our traded universe in which we believe there is a significant untapped signal.

In doing so you will get a chance to tackle a variety of software infrastructure challenges such as:

• Development and optimisation of calibration and benchmarking frameworks.
• Building out and implementing best practices for data preparation and dataset generation pipelines.
• Prototyping and releasing novel predictive architectures especially with respect to time-series models.

You will get instant validation of your work and experience short feedback cycles where going from inception to deployment can be a matter of hours. There will be no red tape to cut and no sales people to consult. It is pure play.

The monthly compensation range is DKK 80-90K for candidates with 3-5 years workex and DKK 90-100K for candidates with 5-10 years workex.

What were looking for:

• Candidates with around 3 years experience or more (some flexibility depending on overall strength of profile) - we have rejected many candidates for being too junior.
• Fluency within mathematics and statistics.
• Experience working with financial data in particular valuation and hedging of fixed-income instruments.
• Experience working with the full Machine Learning stack from data generation through model calibration and real-life validation and monitoring.
• Programming experience with Python in particular data-wrangling and numerical programming.
• Proficiency with computer science fundamentals.
• A scientific and inquisitive mind.

Nice to have

• Experience working with out-of-core datasets.
• Experience working with tools like PyTorch Tensorflow XGBoost and/or Catboost.
• Programming experience with languages like C# and C/C.
• PhD or MSc degree in engineering physics computer science mathematics or economics.

Ideal candidate:

• This is a development-heavy role with a strong focus on hands-on programming and working with data (ideally financial data).
• Open to candidates straight out of a PhD provided they have significant practical experience (e.g. applied projects coding data work) and ideally some software development exposure within finance.
• Candidates should not be purely theoretical - we need evidence of real-world application and implementation experience.
• No strict requirement for a Computer Science degree; candidates from Maths Physics Engineering or similar quantitative backgrounds are suitable if they can demonstrate solid development skills and basic CS knowledge.
• Important that candidates show they are not purely academic and are comfortable in a practical coding-focused environment.
• Financial experience is preferred particularly working with financial data.
• Ideal candidates will have experience in valuation and hedging of fixed-income instruments but this is not strictly required.
• There is flexibility on domain experience - candidates from other areas of finance (e.g. risk) can be considered.
• Ultimately decisions will be based on the overall strength of the candidate (full package) balancing technical ability practical experience and domain knowledge.