Questa posizione è in R2A Labs

Il processo di selezione sarà interamente gestito R2A Labs.

--

**About R2A**

R2A Labs is a young, rapidly growing startup working to break the dependence on fossil-derived materials that underpin so much of what we manufacture and use every day.

We are building technology to rethink bio-based material innovation and develop scalable solutions that compete with synthetic incumbents on both performance and cost. At the core of this is our R2A Lab-in-Loop Engine, a design system that replaces broad experimental trial-and-error with simulation-guided and highly targeted physical experimentation. By bridging the digital and physical worlds we develop high-performing and manufacturable bio-based materials, faster, and smarter.

**About the role**

We are looking for a Software Engineer to help build the data infrastructure and software systems that power R2A’s design engine, connecting simulation, machine learning, and experimental workflows.

- *What you'll do**
- Build and maintain scalable data pipelines that ingest and unify data from multiple computational and experimental sources, making it reliable and usable for downstream systems
- Develop and productionise ML workflows, including surrogate models and optimisation loops, with a focus on robustness, monitoring, and performance
- Design and extend data architectures that support workflows from early-stage research through to process optimisation and scale-up
- Build backend services and job orchestration systems to manage compute workloads, data processing, and model execution
- Improve system reliability by identifying gaps between model outputs and real-world results, and surfacing clear signals to guide iteration
- Develop internal tools, dashboards, and APIs that make data and model outputs accessible and actionable for the team
- Ensure best practices in code quality,



testing, versioning, and reproducibility across the technical stack
- *Your profile**
- Degree in Computer Science, Applied Mathematics, Physics, or a related quantitative field, with 2+ years of post-degree experience building and deploying data-intensive software systems (or PhD equivalent)
- Strong Python fundamentals and demonstrated experience building robust data pipelines across heterogeneous sources and formats
- Demonstrated data engineering or data science capability: designing and managing structured data flows across various sources, building pipelines that remain coherent as the system scales from early discovery through to process optimisation and scalability assessment
- Experience with probabilistic ML or Bayesian methods applied in research or production settings; solid PyTorch experience a strong plus
- Comfortable working across the stack: data pipelines, model training, basic infrastructure, and lightweight internal tooling; good judgment in low-data, noisy-signal environments
- Curious about physical systems and material science, motivated to develop the scientific intuition needed to build software that operates meaningfully inside a materials discovery and scale-up workflow
- Strong builder mindset, motivated by solving hard, high-impact problems
- *Nice to have**
- Familiarity with molecular or materials ML: graph neural networks, equivariant architectures, or materials foundation models
- Experience with HPC environments and/or scientific computing infrastructure
- Experience with process modelling, digital twin frameworks, or engineering scale-up workflows
- *Why join us?**

You will join as a founding technical hire, with direct technical ownership and meaningful equity participation, helping shape a venture designed to bring high-performance materials with a fundamentally positive environmental impact to market.

--

📌 Software Engineer, Machine Learning - Intern (Milano)
🏢 R2A Labs
📍 Milano