Career | <?phpecho $jobTitle;?> | <?phpecho $companyName;?>

Stealth Newco - Machine Learning Scientst

RAVen

Cambridge, MA, US
  • Job Type: Full-Time
  • Function: Data Science
  • Industry: Life Science
  • Post Date: 09/30/2024
  • Website: www.racap.com/venture
  • Company Address: 200 Berkeley Street, 18th Floor, Boston, MA, 02116

About RAVen

RAVen (RA Ventures) is the venture-focused arm of RA Capital Management, LP, a Boston-based biotechnology and life sciences investment firm.

Job Description

About us:
Launched by RA Capital, we are a stealth-stage biotechnology company building a modular, next-gen platform to unlock previously unavailable biomolecule design spaces to accelerate the discovery and development of differentiated therapeutic, diagnostic, and industrial products. Our team is an innovative group of domain experts in AI/ML computational design, advanced synthetic biology, microfluidics, protein engineering, and single-cell profiling who are deeply passionate about the power of the platform to invent the future today. World-class scientific founders from the Broad Institute, cutting-edge technology, and backing from RA Capital come together in a dynamic start-up environment.


About RA Capital:
RA Capital funds and builds healthcare and life science companies using an evidence-based investment approach informed by TechAtlas, a think tank within RA Capital which analyzes scientific and clinical data from academic literature and industry sources to anticipate how breakthroughs might impact industry stakeholders, physicians, patients, and policymakers. TechAtlas' analyses are captured in a unique collection of competitive landscapes, or ‘maps’, that identify competitive therapeutics, diagnostics, research tools, and/or technological capabilities in a given area.


About the Role:
We are seeking an innovative, self-driven, and team-oriented Machine learning Scientist, with a passion for developing cutting-edge platforms at the intersection of AI/ML, biology, synthetic biology, and single-cell technologies. In this role, you will apply your expertise in machine learning and data science to create innovative solutions that advance our platform activities and research and development efforts. You will work closely with cross functional teams to design and implement deep-learning pipelines, analyze large-scale, multi-modal proprietary datasets, and develop new algorithms that integrate seamlessly into experimental platforms. As a key member of a growing and engaged team, you will have the opportunity to take part in leading innovative research and development, and collaborate with a highly skilled, multidisciplinary team in a fast-paced startup environment.



Key Responsibilities:
  • Evaluate, train and deploy deep neural network models using both proprietary and external protein sequence, structure, and function data
  • Establish automated processes to continuously evaluate and improve our protein design methodology
  • Develop and apply deep-learning models to analyze high dimensional biological datasets, including transcriptomics, proteomics, and multi-omics single-cell data
  • Build and maintain database infrastructure for AI/ML, long-term data storage and versioning on AWS
  • Collaborate closely with experimental and computational scientists to develop integrated experimental/in silico pipelines
  • Develop efficient, high-quality code, and data pipelines
  • Present computational approaches and results to the team


Qualifications & Skills:
  • PhD in Computer Science, Machine Learning, Computational Biology, Bioinformatics, Statistics, or a related field
  • Familiarity with Machine learning models for protein design such as ESM, AlphaFold, etc.
  • Experience with conceiving of, implementing, and developing novel machine learning methodologies to analyze large biological datasets
  • Experience in machine learning infrastructure, pipeline building, database maintenance, distributed training and inference, and deployment in cloud computing such as AWS
  • Significant experience in data science and developing and deep learning models and algorithms using modern software libraries such as PyTorch, TensorFlow, or similar
  • Experience working with multi-omics datasets, such as bulk and single cell RNA sequencing, proteomics, and metabolomics
  • Familiarity with NGS data analysis pipelines
  • Strong analytical skills, detail-oriented, and thrives in a fast-paced startup environment
  • Excellent communication skills (written and verbal) and adept at building strong relationships across multidisciplinary teams