Software Engineering/Machine Learning Intern (f/m/*)

Zürich

Cradle

Engineer Better Proteins Faster. AI for modern protein engineering teams.

View all jobs at Cradle

Apply now Apply later

This is Cradle

Proteins are the molecular machines of life, used for many therapeutic, diagnostic, chemical, agricultural and food applications. Designing and optimizing proteins takes a lot of expert knowledge and manual effort, through the use of custom computational and biological tools.

Machine learning is revolutionising this space, by enabling high-fidelity protein models. At Cradle, we offer a software platform for AI-guided discovery and optimization of proteins, so that biologists can design proteins faster and at scale. We are already used by clients across pharma, biotech, agritech, foodtech, and academia.

We're an experienced team of over 40 people. We've built many successful products before and have enough funding for multiple years of runway. We are distributed across two main locations, Zurich and Amsterdam, and are focused on building the best possible team culture.

We offer our employees a very competitive salary, a generous equity stake (for full time employees) in the company and a wide range of benefits and career progression opportunities.

What we are looking for

For this internship we are looking for motivated PhD students in the fields of physics, applied mathematics or machine learning who are excited to peek beyond the science world and join us on integrating ML models in a protein design platform. Be ready to witness first hand what happens when you leave the bits and bytes behind and try to solve challenges with nature’s constraints and complexity. We look for candidates who are not shy to take research papers or ML prototypes and assess their quality and usefulness for protein design.

The internship duration should be 6 months with a flexible start date in 2025.

Project Description:

You'll work on enhancing our protein engineering capabilities by developing automated analysis pipelines for biophysical assay data (NanoDSF and SPR curves). Currently, our biologists manually process these curves to extract parameters like melting temperatures and binding kinetics, which is time-consuming and error-prone. Your primary goal will be to develop robust, automated curve-fitting algorithms that can handle various edge cases and significantly reduce manual processing. In the extended phase of the project, you'll integrate these curve models with protein language models to test if using complete curve data rather than summary statistics improves downstream prediction accuracy.

Responsibilities:

As a machine learning intern, you will be responsible to:

  • Develop robust automated analysis pipelines for high-throughput biophysical assays based on curve-fitting models

  • Transform research prototypes into user-friendly tools for biologists

  • Implement algorithms that can detect edge cases and improve parameter estimation

  • Set up validations using labeled curve datasets to ensure high quality results

  • Integrate curve-fitting models with transformer-based protein language models

  • Collaborate with biologists to understand their workflow needs and pain points

  • Support the team in establishing a stable, high quality and flexible software engineering process

  • Work in a cloud native runtime environment using Google cloud, Kubernetes, Docker and co.

Need to have
  • You are currently enrolled in a PhD program in the field of applied mathematics, physics, machine learning or similar technical field.

  • You write great code. Building, tweaking and productionizing complex ML models does often require advanced coding skills. You will be working in a modern Python codebase.

  • You have worked with deep learning models before and understand the challenges of training a model with close to a billion weights.

Nice to haves
  • Experience with curve fitting, time series analysis, or signal processing

  • You have worked with natural language processing models or protein language models

  • You have experience with protein engineering or computational biology and understand the difficulties of operating in this field

  • Experience with automated data processing pipelines

Culture
  • You are interested and excited about learning a new domain. You will be faced with a lot of new concepts and enjoy learning diverse topics.

  • You are able to communicate well. We are working at the intersection of biology and software where good communication is key.

  • You enjoy taking on challenging projects and are able to process honest feedback.

  • You are kind and work well in teams. We look for team players who contribute to a positive and friendly working environment.

Note: due to government regulations around working permits, this position is only available for EU/EFTA citizens.

Did we pique your interest? We'd love to hear from you. Please use this form to apply directly.

Please note that for roles in Zurich and in the USA, we currently can only consider candidates who have, or are able to independently obtain, a local work authorisation.

A notice about recruitment scams: Please be aware that scammers are posing as us in order to get your personal details or money. We only communicate via @cradle.bio email addresses, we only make job offers after having met you in person at our office in Zurich or Amsterdam, and we never ask you to pay for anything during the interview process

Apply now Apply later
Job stats:  18  4  0

Tags: Biology Deep Learning Docker Engineering GCP Google Cloud Kubernetes Machine Learning Mathematics ML models NLP Pharma PhD Physics Pipelines Protein engineering Python Research Statistics

Perks/benefits: Career development Competitive pay Equity / stock options Flex hours Startup environment

Region: Europe
Country: Switzerland

More jobs like this