Analytic Learning Algorithm Research

Accountabilities:

• Develop numerical and analytical models for learning systems based on modular probabilistic architectures.


• Design and analyze learning algorithms, ensuring theoretical soundness and practical applicability.


• Prove properties of algorithms and validate findings through rigorous experimental evaluation.


• Translate concepts from academic literature into implementable models and system components.


• Contribute clean, well-documented code supporting research experiments and production-aligned implementations.


• Collaborate closely with other researchers to integrate insights across different areas of expertise and support shared objectives.


• Help advance system design by ensuring coherence between mathematical reasoning and software implementation.

Requirements

• Advanced degree in Mathematics, Computer Science, Statistics, or a related quantitative field (PhD or equivalent research experience strongly preferred).


• Strong background in mathematical analysis methods such as optimal transport, information geometry, or continuous optimization.


• Experience working with probabilistic graphical models, including factor graphs or related frameworks.


• Familiarity with tractable density estimation techniques such as normalizing flows, autoregressive models, or probabilistic circuits.


• Ability to bridge theoretical reasoning and practical implementation in code.


• Strong analytical thinking skills with a research-oriented mindset and attention to mathematical rigor.


• Excellent communication skills and ability to collaborate effectively in a distributed research environment.

• Fully remote work setup within a globally distributed, research-focused team (CET-aligned collaboration).


• Opportunity to work on cutting-edge theoretical problems with direct real-world applications.


• High level of autonomy in a flat, research-driven environment.


• Exposure to interdisciplinary applications across finance, physics, and scientific modeling.


• Collaboration with experts in machine learning theory, probabilistic modeling, and applied mathematics.


• Strong focus on intellectual growth, research impact, and publication-quality work.


• Competitive compensation aligned with experience and expertise.

This listing is from ats_lever. View original listing ↗