Staff Engineer, Machine Learning Life Sciences
$148,530–$204,250 year
HybridCambridge, Massachusetts, United States
Job Summary
Build, deploy, and maintain production ML pipelines and infrastructure to serve predictions at scale, integrating systems with genomic, phenotypic, and biological data platforms using AWS and containerization. Train and validate statistical and ML models, prototype new approaches, and evaluate feasibility for production deployment while implementing integrations with third-party tools and foundation models. Drive major workstreams autonomously, collaborating with computational biologists, software engineers, and crop scientists to contextualize heterogeneous biological data and advance trait improvement in crops. Communicate technical results across disciplines and contribute to engineering standards. This role supports Inari's mission to transform agriculture through predictive design and advanced gene editing, leveraging diverse expertise from academia and industry to develop step-change products for a sustainable food system.
Required Qualifications
- MS or PhD in Computer Science, Engineering, Statistics, Mathematics, Computational Biology, or related field (or BS with equivalent experience)
- 6+ years of ML engineering experience with a demonstrated emphasis on production systems
- Proven ability to deploy, maintain, and monitor ML models and pipelines at scale
- Advanced scientific Python (NumPy, Pandas, scikit-learn) and hands-on experience with PyTorch and/or TensorFlow, including training and deploying neural networks
- Experience with AWS (EC2, S3, SageMaker), containerization (Docker), experiment tracking (MLflow), and workflow orchestration (Airflow or equivalent)
- Comfortable interfacing with biologists and life scientists, translating between biological and ML framings, and communicating technical results to diverse audiences
- Track record of owning solutions and deliverables end-to-end — setting direction, aligning stakeholders, and seeing work through to impact — while remaining a collaborative and engaged team member
- This role is based in our Cambridge, MA office and follows our flexible hybrid work model, with time on a weekly basis split between in-office and remote work
Desired Qualifications
- Familiarity with biological data types (genomic, transcriptomic, proteomic), common file formats (FASTA, GFF, VCF, BAM), and sequence modeling methods applied to DNA/RNA/protein data
- Awareness of current research in applying deep learning to biological sequences (e.g., genomic transformers, protein language models)
- Experience with graph neural networks or network analysis tools (e.g., networkx) for modeling complex biological relationships (e.g., gene regulatory networks, protein-protein interaction networks)
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.