Applied Science - Time Series

Highlights

• Design, train and deploy state-of-the-art time-series foundation models.
• Apply Timestral to demanding forecasting for power grids, plants and trading desks.
• Push the frontier in scaling, anomaly detection, classification and embeddings.

What they offer

• Healthcare coverage
• Parental leave
• Retirement plans
• Relocation support
• Wellness programs
• Meal and transportation allowances

Ideal candidate

Low-ego, independent researcher-engineer who loves solving complex real-world problems and moving models from research into production with industrial and financial clients.

Requirements

• Fluent in English with excellent communication skills
• Expert with PyTorch or JAX
• Solid knowledge of modern deep learning and LLMs including pre-training and evaluation
• Experience pre-training or fine-tuning time-series foundation models or large transformers at scale
• Strong background in time-series modelling including probabilistic forecasting and classical baselines
• Writes clean, high-performance, fault-tolerant Python code and contributes independently to large codebases
• Independent, low-ego, collaborative and comfortable with uncertainty