DATA SCIENTIST
What is Funga?
Funga is the forest microbiome company. We are a pre-seed stage startup focused on understanding and improving forests’ sub-soil symbiotic fungi populations to accelerate tree growth. We are aimed at having a huge impact on carbon drawdown, timber production, and improved forest biodiversity.
We are in the earliest stages of spinning out from academia, where our Founder and CEO Dr. Colin Averill has been on the forefront of understanding how variation in the forest fungal microbiome controls forest carbon capture and storage. We have an unprecedented bioinformatics pipeline paired with a proprietary dataset of tree growth statistics and soil fungi genomes that allows us to understand what soil fungi communities should be present for optimal tree growth based on site microclimate, soil chemistry, tree species, and more. So far, academic trials of our technology have shown 30% - 70% faster tree growth just in the first year and the potential to accelerate tree growth by up to 3x over the lifetime of the tree.
The Role
Funga is building a data platform that weaves together fungal genomes, metabolic processes, and local climate so we can identify high performing fungal communities and quantify their effects on tree growth and carbon capture. While a there is a proof-of-concept version of the platform from Dr. Averill’s academic research program, this role will be taking the lead on building out a more robust, scaleable, and insightful next version. We are leveraging best-in-class new technology for deploying bioinformatics infrastructure in cloud computing environments. This role will be responsible for establishing and testing this bioinformatics environment, building out the core functionality of our predictive models based on our sampling program, and delivering key insights to inform our planting program. Finally, current carbon removal verification protocols rely on numerical models of forest ecosystems, and this role will play a key role establishing these models and calibrating them to our datasets.
Candidate Attributes
This is a role for someone hungry to jump into an early stage technology startup as the first leader focused solely on data science and platform development. Someone who is successful in this role will have enough experience in data science and software development to know how things work, but also be creative and open-minded enough to develop innovative solutions to the unique ecological questions our approach presents.
Key Responsibilities
-
Build and maintain bioinformatic infrastructure in partnership with Latch Bio (cloud platform) to house Funga’s datasets, analysis pipelines, and development environment.
-
Replicate a past published bioinformatic analysis. Optimize this code to be easily used and read by others.
-
Establish basic microbiome sequence processing pipeline using dada2 or similar.
-
Implement our own, custom phylo-genomic analyses, currently developed in R and python.
-
Run feature engineering experiments to improve Funga’s ability to identify high performing communities of fungal microorganisms.
-
Review numerical models of forest carbon cycling used by verification agency protocols and implement as necessary.
-
Document the development environment and pipeline architecture.
-
Collaborate with our business, forestry, and scientific teammates to hit key strategic goals.
Required Attributes
-
3+ years of experience in a data science role in academia or at a technology company.
-
Familiarity with R and Python.
-
An independent strategic thinker and compassionate leader. Independent execution is essential.
-
Interest in growing into a leadership role within our data science team.
-
A strong drive to build a historically significant company.
-
Dedication to decarbonization, forestry, and biodiversity.
-
Strong written and verbal communication.
Additional Desired Attributes
-
Experience with genomic data processing and analysis methods.
-
Experience with terrestrial carbon cycle science and analysis.