Lead Scientist - Machine Learning at MoGen
About the role
OPPORTUNITY MoGen is currently seeking a Lead Scientist with experience in ML&AI approaches in genomics.
The successful candidate will work collaboratively with our interdisciplinary team of experts in single cell technology, metabolic disease and CRISPR technologies. The candidate will lead the technical development of the machine learning platform and be highly influential in experimental design.
This position requires adaptability, strong organizational and communication skills, and the ability to work both independently and collaboratively in a dynamic team-oriented environment.
- Provide input on experimental design
- High involvement in hiring additional computational team members
- NGS data analysis using python, R or similar
- Training of models using high-throughput datasets using modern ML tools such as Tensorflow, Pytorch
- Regular communications of data and analysis results to team members
- Collaborate on project budgeting and scope management
REQUIRED QUALIFICATIONS No specific degree requirements. Degree in a quantitative field is highly desirable. Comfortable with modern ML tools. Track record of collaborative work in machine learning. Experience with genomics datasets is highly valued.
PREFERRED QUALIFICATIONS Experience with containerization and deployment of ML models. Experience with variant annotation in sequencing data.
Why you should join MoGen
MoGen is developing a genetic test to detect preventable intellectual and developmental disabilities in babies caused by metabolic disorders. If these conditions are caught before a person starts developing symptoms they can be given simple treatments such as dietary changes, enzyme replacement therapy and vitamins. Currently, these conditions are screened for at birth, but this misses >50% of cases. We can do better.
Our unique approach couples two cutting edge approaches: (1) Generation of rich datasets that systematically mutate the genes involved in these disorders and (2) Using this data to train advanced models using ML+AI approaches.
There are many reasons why our technical approach is awesome, but here are the top 3:
- We do not require tons of patient data to generate extremely good models, which can be hard to do with rare diseases.
- Since our model doesn't rely on patient data it is very robust against lack of ethnic diversity in the samples.
- We can expand into whatever disease category we want.
Curing intellectual or developmental disabilities is super hard and may not ever be possible. But preventing some of them is within reach in the next year or two and is an inevitability. As a company our mission is to accelerate our arrival to this future.