AI system for knowledge representation and transparent reasoning
PlantingSpace builds an AI system that accurately represents knowledge and uncertainty from diverse sources, enabling transparent problem-solving and insight discovery. It serves as analysts, research assistants, or data scientists across domains by providing probabilistic answers with visible reasoning. The system uses category theory, Bayesian methods, and deep learning for reliable, interpretable AI.
Manage engineering roadmap, lead quarterly planning, and coordinate complex technical features from idea to implementation while staying hands-on with development tasks. Requires software engineering background combined with organizational and technical product management experience.
Build end-to-end features across frontend (TypeScript/React), BFF (tRPC/drizzle/Postgres), and backend (Julia/Rust) for a probabilistic modeling platform used in finance and research.
Conducts research in applied category theory to formalize semantics of probabilistic DSLs and develop models for real-world phenomena like relationships, dynamical systems, and natural language. Requires PhD-level expertise in category theory and functional programming skills.
Develops product demos for quantitative modeling system in finance and scientific research, productizing research software by implementing use-case applications, identifying strengths/limitations, and improving the product. Requires experience commercializing research software and applied mathematical modeling.
Develops modular probabilistic models and algorithms for Bayesian statistical inference and machine learning in Julia, focusing on backend implementation, scaling statistical procedures, and integrating into large software systems for finance and research applications.
Builds program synthesis pipeline for modular probabilistic models in finance and research applications. Requires experience with complex algorithms like graph theory and compilers, plus collaborative software engineering practices.
We are seeking full-time researchers to develop and analyze learning algorithms for a system that represents domain knowledge as modular probabilistic models. The role involves theoretical problems with immediate implementation applicability in finance and scientific research.