Computational Biologist / ML Scientist
South San Francisco
Platform Engineering /
On-site
Amber Bio is a biotechnology company pioneering new gene editing modalities using multi-kilobase edits to reach previously undruggable patient populations. Founded by pioneers in the CRISPR field from leading institutions for gene editing research, the company is developing a first-of-its-kind RNA writing platform that can correct thousands of bases at once, thereby correcting genetic mutations safely and reversibly. Multiple openings are available on a rapidly growing team. As an early team member, you will have the opportunity to contribute to strategic planning and future hiring. If you are interested in building a new frontier in genetic medicine, please apply through LinkedIn or directly on our website (www.amber.bio).
If you are a skilled Computational Biologist or ML Scientist with a passion for applying machine learning approaches to (one of: model/design/engineer) biological sequences, we encourage you to apply and join our innovative team.
Job Description: Computational Biologist / ML Scientist
Responsibilities
- Implement state of the art methods to predict RNA and protein function from sequence.
- Analyze and preprocess experimental data, including DNA, RNA, and protein sequences, high throughput screening data and structural data for model training and validation.
- Plan and execute machine learning experiments, and set milestones and timelines to achieve research objectives.
- Collaborate with wet lab scientists to align ML experiments and integrate model insights into the design process
- Fine-tune models using custom datasets and external resources to achieve high predictive performance.
- Collaborate with gene editing and molecular biology experts to integrate model insights into the design process.
- Stay updated with the latest advancements in machine learning techniques, RNA/protein structure prediction, and gene editing technologies.
- Publish results in relevant conferences and peer-reviewed journals.
- Design, build, and maintain computational pipelines to process, analyze, and interpret next-generation sequencing (NGS) data, including variant calling and differential expression analysis.
Qualifications
- Ph.D. in Computer Science, Bioinformatics, Computational Biology, Molecular Biology, or related fields. Strong academic background in machine learning and molecular biology is preferred.
- Minimum of 2 years of practical experience in developing machine learning models, with a focus on RNA and protein structure prediction, acquired during PhD studies or a post-graduate role.
- Proven track record of addressing high impact questions in biology using statistical and machine learning techniques.
- Understanding of gene editing techniques, such as CRISPR-Cas9.
- Experience with RNA and protein structure prediction tools and databases (e.g., Rosetta, RNAfold, PyRosetta, AlphaFold).
- Proficiency in Python and PyTorch / TensorFlow and other bioinformatics tools.
- Excellent communication skills and the ability to collaborate effectively with technical and non-technical teams.
- Strong analytical skills with the ability to design creative solutions for complex molecular challenges.
Preference will be given to those who display
- High motivation, with a strong work ethic and dedication to generating impact.
- Long-term personal vision with defined career goals.
- High EQ with team-oriented thinking.
If you have a passion for advancing gene editing technologies and desire to be part of a pioneering biotech company, we encourage you to apply and join our ambitious team.
Amber Bio is an equal-opportunity employer and encourages applications from candidates of diverse backgrounds. We value diversity and are committed to creating an inclusive and supportive work environment for all employees.
