We are building a system that represents domain knowledge as modular probabilistic models. Users compose them into larger structures, the system enforces consistency across them, and uncertainty is propagated across model boundaries autonomously by the composition itself.

You will implement models that our users need, inside of our framework. Our current applications range from equity valuation and financial distress monitoring to particle physics.

What is interesting is that the automated compositional machinery supports models from very different domains without special-casing.

What you will do

• Work with the product team to define what a model needs to do, then own it through to something a user can run

• Define and document the implementation approach for harder modelling problems

• Write code that is clean enough to be maintained by others and fast enough to run at the scale users need

• Establish that a model is correct, not just that it executes

• Find where the framework constrains the model you are trying to build, and feed that back concretely enough to act on

• Contribute to the surrounding production system

Useful experience

• Taking models into production for external users and remaining accountable for their correctness in use

• Applied mathematical modelling in finance and/or scientific applications

• Strong foundation in computer science algorithms and data structures

• Experience in a collaborative, commercial software engineering environment, working on large codebases and using practices like CI/CD, testing, and code reviews

• Julia, or usage of some more functional or typed languages, e.g. Rust, OCaml, Clojure, C++, or Haskell

• Profiling and performance optimisation

• Advanced degree in Mathematics, Physics, Engineering, Computer Science, or Statistics

Where you might be coming from

• Scientific or engineering software, where you implemented solvers or physical models into a product with external users

• A risk or analytics vendor, where you built the model library itself rather than configuring it for clients

• A research background in a computational field, followed by several years shipping in a commercial product team

How we work

• Hierarchical goals, not personal hierarchies: We organise around a transparent tree of goals and tasks. Every quarter we plan milestone goals, which branch down into smaller and smaller tasks. This tree is the foundation of how we organise, not a side tool.

• Transparency: Everyone should have access to every opportunity in the team that they can realistically handle. All goals, tasks, and the reasoning behind them are visible to everyone.

• Decisions become tasks: When something is discussed and decided, it gets captured as a task in the right place in the tree, so that nothing dissipates as hot air.

• Written and asynchronous by default: We are fully remote and document our learnings in writing. Communication happens transparently in shared channels, not in private threads and one-on-ones.

• Growing from leaf to tree: New joiners start from smaller leaves of the tree and work themselves up to ownership of larger branches as trust and understanding build. Teams form around topics and dissolve when the work is done; people move to where they are most useful.

Want to know more?

On our website you can find more about our team and work culture, as well as example tasks that share some insight into the type of things team members are working on.

• What we do: https://planting.space/

• Ways of work: https://planting.space/org/

• Team culture and example tasks: https://planting.space/joinus/

Our team works fully remotely, and mostly within the CET timezone.