Software Engineer- Deep Learning


About Us

Evozyne is a new, energetic and innovative company that creates synthetic proteins that have the potential to improve the world. With a recently completed 30,000 square-foot office and lab space in Chicago’s Lincoln Park neighborhood, we are embracing revolutionary science and artificial intelligence to find answers to critical global challenges like increasing crop yields, curing diseases, making tomorrow’s materials and cleaning our environment. Evozyne, a portfolio company of life science innovator Paragon Biosciences, is strongly positioned to make meaningful, positive impact locally and globally for years to come. Learn more about who we are, visit

About Our Team

The Computational Team at Evozyne is a bit different – a bit of code, a bit of creativity, combined with a byte of humility.

Machine learning is at the core of Evozyne’s technology for protein design, and we make it happen. We are intimately involved in the research and development cycle, regularly collaborating with molecular biologists and lab scientists to generate optimal protein sequences for tough problems facing the world.

We are a small, nimble team with a diverse range of expertise and backgrounds. We embrace modern software best practices and strive for high code quality. We love Python and JavaScript but aren’t afraid to dig into C++ or R or Haskell or Rust if we need to (even if we admittedly aren’t experts). Relational databases are great, and so are graph databases. We train neural networks daily, but we also know when an if statement is good enough. Team collaboration is our bread and butter, from code reviews, Slack support channels, lunch and learn sessions, flexibility for hybrid remote/office work, tech skill development, to mentorship of junior team members as well as leadership opportunities.

We are hiring and building our team culture for the long run: we want software engineers and data scientists who will grow with us, who find satisfaction and motivation from their work as well as the time to thrive in their own lives outside of the office. Diversity, equity, and inclusion are key drivers to the success of our team, whether that is in the form of background, personal identity, perspective, or opinion. We invite the bit of difference you can make on our team.

Job Description


This position is focused on the development of a greenfield software platform that enables data-driven protein design. The position will be building and deploying a scalable machine learning system that interfaces with Evozyne's state-of-the-art molecular biology laboratory, accelerating our capability to train and iteratively improve our generative neural network models learned from experimental data. The position will collaborate closely with data scientists to integrate back-end services and databases with Evozyne’s bioinformatics and machine learning research efforts. The successful candidate will be able to humbly take the lead on software development efforts yet also be able to learn from and coordinate with other computational team members, as well as contribute to the overall exciting, positive atmosphere of our early-stage startup company.


  • Responsibilities will naturally grow over time as you become more familiar and comfortable with the role. The follow items are what you can expect to be doing in the span of a few months to a year on our team:
  • Develop and deploy a scalable and robust protein design machine learning platform with user-friendly interfaces, thorough testing, and excellent documentation.
  • Interface closely with the computational teams developing our bioinformatics and deep learning back ends as well as wet-lab teams in deploying the software.
  • Maintain and continually improve our software systems and databases by incorporating additional features, integrations, and bug fixes.
  • Be a productive collaborator across departments in our early-stage company.


  • Technical skills are critical to this role, but nobody knows everything. We are judicious about tech skills and know they can be honed over time in this role. Not every single box below needs to be checked at the time of starting for you to be successful on our team:
  • Strong programming skills and extensive experience with Python and common tools in the data science stack, including but not limited to: Flask, numpy, scikit-learn pandas, poetry, Jupyter.
  • Proficiency and familiarity with neural networks and deep learning libraries, including PyTorch, TensorFlow, and Keras.
  • Proficiency and familiarity with modern software development tools and practices: Linux / Unix, Docker, git (GitHub, GitLab), CI/CD, QA testing (unit, integration, performance, etc.)
  • Experience with distributed service architectures and cloud providers such as AWS, GCP, or Azure.
  • Familiarity with various high-performance computing and parallel programming concepts and technologies: GPUs, CUDA, multithreading, OpenMP, MPI
  • Familiarity with SQL and NoSQL databases, ETL data pipelines, data structures, functional programming, and/or object-oriented programming patterns.
  • Experience with best practices in software design, prototyping, development, testing, documentation, code review, deployment, support, and troubleshooting.
  • Curiosity and ability to work and solve problems in interdisciplinary teams.

Nice To Haves

Surprise us! Here are just a few things we think could be helpful for your success on our team:

  • Involvement and/or participation in science and technology community forums, events, conferences, or outreach programs.
  • Experience with interactive data visualization in web apps.
  • Scientific knowledge or background in chemistry, biology, bioinformatics, and/or molecular genetics.
  • GitHub profile, web links, personal web page, or portfolio with examples of code and/or projects.

Education, Experience and Certifications

  • Education: A Bachelors, Masters, or PhD degree in computer science, software engineering, and/or allied field; or equivalent skills and knowledge gained through sufficient industry experience or other program.
  • Experience: The ideal candidate will have 3+ years of prior industry experience in the design, development, deployment, and support of a cloud-based software platform.
  • Compensation will be determined based on experience and qualifications.

Required Documents:

Resume or CV

Cover letter – Have something important you’d like us to know about you? Tell us!

Apply now