At Ohalo, we are building the future of agriculture with our breakthrough Boosted breeding technology and seeking a Quantitative Geneticist to be a principal architect of the computational engine that drives our entire crop improvement strategy.
Requirements
- Expert-level proficiency in Python and its scientific computing stack (e.g., NumPy, SciPy, Pandas, Scikit-learn). Demonstrable experience building modular, testable, and maintainable code is essential.
- Hands-on experience using generative AI tools (e.g., GitHub Copilot) to accelerate the development of scientific code.
- Deep theoretical and practical understanding of mixed models for genetic evaluation (e.g., GBLUP, ssGBLUP).
- Proven experience with Bayesian statistics, applying methods such as Bayesian GBLUP, hierarchical models, and clustering using MCMC or variational inference.
- Familiarity with decision theory and online optimization frameworks (e.g., multi-armed bandits, Thompson sampling) for resource allocation.
- Experience with or interest in applying genomic foundation models (e.g., Evo2, other LLM-like architectures) to learn from large-scale sequence data.
- Experience with machine learning algorithms (e.g., XGBoost, Ridge Regression) as applied to genomic data.
Responsibilities
- Genomic Prediction & GWAS: Design, build, and validate the primary statistical models (e.g., GBLUP, ssGBLUP, GWAS) that form the foundation of our predictive capabilities, translating genotype and phenotype data into actionable insights.
- Breeding Simulation: Evolve our in-house breeding simulation platform to run complex, large-scale scenarios. Your models will answer critical strategic questions about resource allocation, risk management, and the optimal path to achieve our breeding objectives.
- Pipeline Optimization: Move beyond prediction to prescription. Design and implement online optimization models (e.g., using multi-armed bandits, online learning, metaheuristics) to create a self-improving system that dynamically allocates resources and maximizes the rate of genetic improvement.
- Portfolio Management & Utility: Develop and integrate multi-trait utility functions that align our selection strategy with market needs and product profiles. You will help manage the entire breeding portfolio as a strategic asset.
- Accelerate Research with AI: Act as a force multiplier by leveraging modern AI tools across the research lifecycle. This includes using LLMs for hypothesis generation, pioneering the use of genomic foundation models (e.g., Evo2), and using AI-assisted tools to write, debug, and document production-quality code.
- Drive Cross-Functional Impact: Serve as a critical scientific partner to domain experts (breeders, plant scientists), Machine Learning Engineers (MLEs), and Data Engineers (DEs). Proactively translate breeding objectives into modeling requirements and ensure your solutions are seamlessly integrated into our operational workflows.
- Uphold Statistical Rigor: Collaborate with fellow quantitative scientists to champion statistical integrity across the organization, from experimental design to model validation and interpretation.
Other
- M.S. or Ph.D. in Quantitative Genetics, Statistical Genetics, Plant Breeding, Biostatistics, Operations Research, or a related computational field.
- 2-5+ years of hands-on experience applying quantitative principles in a research or industry setting. A strong portfolio of projects demonstrating the application of predictive modeling and/or simulation is highly desired.
- A proven ability to work effectively in a cross-functional team. You must be able to translate complex technical and scientific concepts for different audiences and work collaboratively to turn models into real-world impact.
- No visa sponsorship is available for this position at this time.
- No recruiters please.
