At Phantasma Labs, we’re building smart software that helps factories plan better. Our AI co-pilot helps factories schedule production more efficiently, adapt to changes faster, and make the most of available resources, without needing tons of data or complicated tools. Instead of relying on massive historical datasets, our models are trained in simulated factory environments using reinforcement learning, which helps us find better solutions much faster than traditional systems. We work with manufacturers across Europe and the US and team up with ERP and MES providers to bring our solution directly into real production workflows. We’re based in Berlin, but remote-first, so you don’t have to be here to join us. We’re a lean, international team with big ambitions, building what we believe is one of the most advanced production planning tools in the world.
Tasks
* Write robust, scalable, and production-ready Python code
* Provide code reviews, guidance, and mentorship to fellow developers to maintain high coding standards
* Write unit tests and integration tests (unittest, pytest, etc.)
* Design, engineer, and optimize features in the digital twin for Reinforcement Learning (RL) simulations using Python (Python data structures, NumPy, Pandas, etc.)
* Create, optimize, and maintain training and evaluation scripts (for RL agents)
* Set up and maintain Python environments using modern tools (uv, conda, etc.)
* Work collaboratively using git (GitHub)
* Participate in customer calls to understand and translate requirements into actionable technical features.
* Brainstorm ideas to improve the RL agent, including algorithms, rewards, and architecture.
Requirements
Must haves
* A background in Computer Engineering/Mathematics/Machine Learning/Industrial Engineering or related field
* 5+ years of Python experience
* 2+ experience in factory shopfloor operations as engineer or planner
* Or Alternatively 2+ years experience in ERP/MES systems for factories
* Strong grasp of manufacturing processes across various domains like discrete manufacturing, line production, and engineer-to-order, etc.
* Basic understanding and experience in developing/application of RL algorithms
Nice to haves
* 3+ experience in factory shopfloor operations as engineer or planner
* Or Alternatively 3+ years experience in ERP/MES systems for factories
* Research experience in developing RL algorithms
* CI/CD pipeline experience (GitHub actions)
* Experience in using libraries like Pytorch, Optuna, MLflow
Benefits
* Ownership from day 1: small team, fast feedback, visible results
* Collaborate with a strong team: work alongside highly skilled ML specialists working on cutting-edge AI optimization, and experienced software engineers building the production-grade systems that bring it to life
* A supportive, open culture: clear communication, strong collaboration and flat hierarchies
* Flexible working hours & hybrid setup: work remotely or from our Co-working space in Berlin Mitte – whatever helps you do your best work
* A company laptop to support your work
Sounds Like a Fit?
If this sounds like your type of challenge, we’d love to hear from you! Just fill out our short application form to tell us who you are, what you’ve built so far and why this role excites you.
At Phantasma Labs, we’re building smart software that helps factories plan faster and better. Our AI figures out how to schedule production more efficiently, adapt to changes faster, and make the most of available resources – without needing tons of data or complicated tools. We train our models in simulated factory environments (Digital Twins) using reinforcement learning, which lets us find better solutions way faster than traditional systems. We work with mid-sized manufacturers across Europe and team up with ERP and MES providers to bring this tech directly into real production workflows. We’re a lean, international team with big ambitions. Backed by top investors and working closely with global industry leaders, we’re on a mission to revolutionize manufacturing efficiency with cutting-edge AI tech.