Careers at Kausalyze

Build the science behind better plant decisions.

Industrial decisions need more than correlation. We are building causal AI that helps engineers find the cause of a recurring problem, test a change and understand its expected impact.

Join a team bringing chemical engineering, causal research and software into the same problem.

The work

Hard questions.
Real process consequences.

How do you separate a driver from a symptom? How do you make the evidence inspectable? How do you turn a finding into a change an engineer can evaluate?

01 / CAUSAL RESEARCH

Find the relationships that matter.

Build causal models from historian data, process drawings and lab results. Account for time delays, connected equipment and the physical constraints that shape a process.

Causal discovery · Process physics · Time-series data
02 / PRODUCT & ENGINEERING

Make the reasoning usable.

Give engineers a way to inspect causal paths, review evidence and test interventions. Turn research workflows into software they can use to evaluate an operational decision.

Software engineering · Model workflows · Evidence
03 / INDUSTRIAL APPLICATION

Connect the model to the plant problem.

Work with process engineers to validate important relationships, investigate recurring failures and quantify the expected value of a prescribed change.

Engineering validation · Root cause · Expected impact
How we work

Rigorous about the evidence. Close to the engineers.

We are a small team working across research, product and industrial application. The work needs all three perspectives.

Meet the team
  1. Show your evidence.

    Make assumptions explicit and test the explanation. A finding is useful when someone else can inspect how you reached it.

  2. Build with the people who use it.

    Engineers are accountable for what happens in a unit. Their questions and process knowledge shape the models and the product.

  3. Follow the problem through.

    Connect the research to a usable workflow and a measurable plant outcome. Work across disciplines to resolve what sits between them.

  4. Take ownership. Share the reasoning.

    In a small team, you can shape the approach as well as the implementation. Document what you learn so others can build on it.

Opportunities

Start a conversation.

Interested in the problem we are solving?

We welcome introductions from people working in causal AI, process engineering and software.

Tell us what you have worked on, where your expertise lies and why you want to build with Kausalyze. A link to a project, paper or portfolio is a useful starting point.

Use our contact form to introduce yourself and let us know where you are based.

Introduce yourself

Understand what you could help build.

See how plant data, process physics and engineering validation come together in a causal model.

See how it works