Ohalo is looking for a Machine Learning Engineering Lead to convert quantitative-genetics research into production systems that accelerate crop improvement, shaping how breeders make crossing decisions and driving agricultural productivity.
Requirements
- Expert Python plus one ML framework (JAX/NumPyro, TensorFlow, or PyTorch)
- Strong grasp of microservices, Docker/Kubernetes, and cloud data platforms (BigQuery, Vertex AI, etc.)
- Practical experience with genomic-prediction, GWAS, or related quantitative-genetics models
- Proficiency in Bayesian/MCMC methods
- Comfortable designing batch, streaming, and event-driven pipelines
- Experience with Pub/Sub, Kafka, or equivalent
- Bonus points for: Heterotic-group analysis, trait-mapping for fertility, Nextflow pipelines, or high-throughput phenotype imaging.
Responsibilities
- Lead technical strategy & architecture for statistical-genomic services—from MCMC breeding simulations to real-time breeding-value prediction APIs.
- Design, build, and maintain scalable ML pipelines on GCP (or the best-fit cloud) using Python, BigQuery/Spark, Kubernetes, and CI/CD best practices.
- Advance statistical rigor by championing Bayesian & mixed-model methods (Stan, PyMC, BGLR, TensorFlow Probability) and ensuring reproducible research-to-production transitions.
- Integrate genomic technologies: GWAS workflows, marker-assisted selection analytics, heterotic-group analysis, and large-scale phenotype/genotype feature stores.
- Own model-ops lifecycle: automated testing, containerized deployment, continuous monitoring, and A/B evaluation against breeding KPIs.
- Collaborate cross-functionally with plant scientists, data engineers, and the automation group to ingest high-throughput phenotyping data and close feedback loops.
Other
- Lead technical strategy & architecture
- Mentor & grow a small team—provide technical guidance, establish code-review norms, and cultivate a culture of rapid, well-engineered experimentation.
- Report progress & roadmap trade-offs directly to the executive team, translating scientific ambition into clear engineering milestones and OKRs.
- 3–5 years building production ML/AI systems, with at least 1–2 years in a technical-lead or mentoring role.
- Leadership & communication – Able to set direction, give candid feedback, and bridge domain-scientist ↔ engineer conversations with clarity.
