Terrana Biosciences is seeking to advance sustainable farming solutions through precision technologies that ensure environmental safety and regulatory compliance by developing innovative RNA-based products.
Requirements
- Familiarity with core problems and methods in computational biology.
- Familiarity with DNA/RNA synthesis constraints, codon optimization, and vector design
- Experience with ontology design, data labeling, and metadata curation for heterogeneous biological datasets.
- Experience designing closed-loop ML systems or integrating active learning in high-throughput experimental contexts.
- Deep knowledge and expertise in machine learning, including generative foundation models, multimodal architectures, uncertainty estimation, and transformer-based methods.
- Hands-on experience with deep learning frameworks and scalable computing environments (AWS preferred).
- Strong software engineering skills, with experience in Python or R and best practices for maintainable, reproducible code.
Responsibilities
- Design and implement ML/AI models to optimize in vivo RNA and peptide synthesis, dynamics, mobility, and localization in plant systems.
- Predict how primary, secondary, and tertiary structures of RNA and peptides relate to replication, mobility, and physiological impact in plant cells.
- Develop and refine generative models to design novel RNA and peptide sequences optimized for uptake, trafficking and expression within plant systems.
- Design and curate scalable, queryable databases tailored for biological sequence data, structural annotations, and experimental results to support generative learning and model retraining.
- Extend existing proprietary and public ML tools into discovery platforms that infer unknown RNA and peptide sequences from phylogenetic and functional data.
- Translate high-dimensional molecular data into testable biological hypotheses by uncovering principles of RNA and peptide behavior in plants and microbes.
- Increase experimental success rates by developing predictive models that prioritize high-potential constructs, accelerating Terrana’s test-and-learn cycles.
Other
- Ph.D. or equivalent research experience in computer science, physics, biology, bioengineering, or a related field.
- Demonstrated ability to work with domain experts to translate biological constraints into machine learning objectives, especially for optimizing transport, stability, or expression in vivo.
- Excellent communication and collaboration skills, with proven ability to translate between biologists and data scientists to define ML objectives rooted in real-world biology.
- Track record of improving workflows through automation, AI integration, or software tooling.
