🌱 At .omics, we’re building foundation models for plant biology—turning genomic and multi-omics data into the next generation of tools for trait discovery and predictive breeding. The goal: develop crops that can better withstand pests, viruses, and climate stress, helping agriculture adapt to the challenges of a changing environment.

Position Overview

We’re looking for an Applied AI Scientist to ensure our models don’t just scale, but deliver targeted biological impact at large scale. You’ll contribute to pre-training efforts and lead the development of applied models for concrete use cases in trait discovery and breeding—translating cutting-edge AI into tools that can shape the future of sustainable agriculture.

🎯Key Responsibilities

• Architecture Selection & Design: Exercise best technical judgment to select and design the most appropriate AI architectures for specific biological use cases, building upon our foundation embedding layers to address plant biology questions with optimal precision and interpretability.
• Applied Model Development: Develop sophisticated modeling approaches that effectively combine genomic, transcriptomic, and phenotypic data to predict plant traits and guide breeding decisions, choosing from the full spectrum of AI methodologies based on biological context and data characteristics.
• Multi-Modal Integration: Create architectures that strategically integrate our embedding layers with structured biological knowledge, environmental data, and experimental results, selecting the most suitable approaches for each type of biological relationship and prediction task.
• Production Model Development: Translate research prototypes into robust, scalable models that can be deployed in real breeding programs and agricultural applications, ensuring models are both technically excellent and practically useful for agricultural decision-making.
• Biological Validation & Interpretation: Collaborate with biological researchers to validate model predictions against experimental data, interpret model outputs in biological context, and guide future data collection strategies to continuously improve model performance.
• Strategic Model Architecture: Design comprehensive modeling strategies that leverage the strengths of different AI approaches (including but not limited to transformers, graph-based methods, ensemble techniques, and classical ML) based on the specific requirements of each trait prediction and genetic design challenge.

🙂Qualifications

Required Qualifications

• Applied AI Experience: Proven experience developing and deploying diverse machine learning architectures in production environments, with demonstrated ability to select and adapt the most appropriate modeling approaches for different problem domains and data characteristics.
• Multi-Modal Learning: Strong background in integrating diverse data types (structured, unstructured, sequential, relational) into unified modeling frameworks, with experience evaluating different integration strategies based on data properties and use case requirements.
• Architectural Decision-Making: Expertise in evaluating and selecting from a broad range of AI methodologies (including deep learning, classical ML, graph-based approaches, ensemble techniques, and hybrid methods) based on problem context, data availability, and performance requirements.
• Foundation Layer Integration: Experience building sophisticated models on top of pre-trained embeddings or foundation layers, with ability to design downstream architectures that effectively leverage learned representations for specific applications.
• Production ML Systems: Experience with MLOps, model deployment, monitoring, and maintenance in production environments, including experience with distributed systems and scalable architectures that can handle diverse model types.
• Programming Excellence: Expert-level coding skills in Python and deep learning frameworks (PyTorch, JAX), with experience implementing and optimizing various AI architectures and ability to prototype rapidly across different modeling paradigms.
• Cross-Functional Collaboration: Demonstrated ability to work effectively with domain experts to understand requirements, translate business problems into technical solutions, and make informed architectural decisions based on both technical and domain considerations.
• Self-starter and autonomous.
• Low-ego.
• Collaborative and have a real team player mindset.

Preferred Qualifications

• Biological Domain Knowledge: Familiarity with plant biology, genomics, or agricultural applications, including understanding of biological data types and the unique modeling challenges they present.
• Advanced Degree: Ph.D. in Machine Learning, Computer Science, Computational Biology, or related field with focus on applied research and demonstrated ability to select optimal approaches for diverse problem domains.
• Industry Experience: Background in biotech, agtech, or similar applied research environments where model architecture decisions directly impact business outcomes and where diverse AI approaches are evaluated and deployed.
• Technical Leadership: Track record of making strategic technical decisions about model architecture and approach selection, as evidenced by successful deployment of varied AI solutions or leadership roles in applied ML projects.
• Broad AI Methodology Experience: Hands-on experience with multiple AI paradigms (attention mechanisms, graph-based learning, ensemble methods, probabilistic models, etc.) and ability to assess their relative strengths for different types of biological modeling challenges.
• Open Source Contributions: Active participation in applied ML communities through contributions that demonstrate thoughtful approach selection and architecture design for real-world problems.

❓Benefits

• Competitive salary package
• Opportunity to work in a pioneering techbio environment
• Flexibility to work from home a few times per week
• Choose your preferred laptop to best support your work
• Health Insurance - Comprehensive coverage through Alan's most premium plan (50% contribution from the employer)
• Professional development support, including conference attendance and learning opportunities
• A dynamic and collaborative work culture designed for innovation and impact