Overview

We are a prop-trading company that combines the agility of a startup with the resources of a high-performing fund. Our team is focused on developing cutting-edge strategies, and working with us means not just advancing technology, but also being part o…

Responsibilities:
  • Researching, developing, and deploying cutting-edge machine learning models for forecasting complex, high-dimensional time series — from market signals to macroeconomic indicators and alternative data.
  • Building ML pipelines from scratch: data ingestion, feature processing, modeling, calibration, and monitoring.
  • Designing custom validation and testing approaches for non-stationary data, including regime shift detection and adversarial evaluation.
  • Working with large-scale data sources — tick-level, satellite, transactional, web-scraped — and transforming them into structured features.
  • Collaborating with quants and engineers to integrate ML models into real-world investment processes.
  • Contributing to strategic research initiatives, including causal inference, representation learning, and attention-based models for time series.
Required Qualifications:
  • Experience: 4–8 years of work experience, ideally a mix of academia and industry.
  • Experience: Publications at top AI venues (NeurIPS, ICLR, ICML) in the fields of Time Series or Signal Learning.
  • Experience: Experience building models that forecast market or alternative signals, macroeconomics, commodities, or sentiment.
  • Experience: Participation in building an ML research culture: internal toolkits, mentorship, and open science practices.
  • Skills & Education: Expertise in deep learning for time series: Temporal Fusion Transformers, DeepAR, N-BEATS, PatchTST.
  • Skills & Education: Knowledge of causal inference and counterfactual reasoning for time series.
  • Skills & Education: Experience in multi-modal learning (time series + tabular data + text).
  • Skills & Education: Proficiency with the ML stack: PyTorch, HuggingFace, DVC, Docker, etc.
  • Skills & Education: Skills in model validation for non-iid data: custom cross-validation strategies, regime-aware data splits.
  • Skills & Education: Ability to build end-to-end ML pipelines — from data ingestion to production inference.
  • Skills & Education: Master’s degree or PhD in a quantitative field (Physics, Mathematics, Computer Science, or related areas).
  • Skills & Education: Languages: Russian, English.
Note:

Our intelligent job search engine discovered this job and republished it for your convenience.
Please be aware that the job information may be incorrect or incomplete. The job announcement remains the property of its original publisher. To view the original job and its full details, please visit the job's URL on the owner’s page.

Please clearly mention that you have heard of this job opportunity on https://ijob.am.