Full-Time

Head of AI Structural Biology Research

Posted on 9/3/2024

Absci

Absci

51-200 employees

Biotech company specializing in protein production

Biotechnology
Healthcare

Compensation Overview

$245k - $330kAnnually

+ Equity Package

Senior, Expert

New York, NY, USA + 1 more

More locations: Vancouver, WA, USA

Hybrid role with options for remote work or onsite presence in New York, NY or Vancouver, WA.

Category
Computational Biology
Genomics
Biology & Biotech
Required Skills
Data Structures & Algorithms
Requirements
  • Ph.D. in Computer Science, Machine Learning, Computational Biology, or a related field
  • 5+ years of experience in AI/ML research, with at least 2 years in a technical lead role
  • Strong publication record or demonstrated expertise in areas such as generative AI, deep learning, or computational biology
  • Experience applying AI techniques to biological problems, particularly in protein design or drug discovery
  • Proven track record of leading successful AI research projects and translating research into practical applications
  • Excellent communication skills, able to explain complex AI concepts to diverse audiences
  • Strong problem-solving skills and ability to think critically about AI research challenges
Responsibilities
  • Lead and manage a team of 4-6 AI/ML researchers, providing technical guidance and fostering a culture of innovation
  • Oversee the development and implementation of novel AI/ML models and algorithms, particularly in areas like amino acid sequence generation and 3D protein structure prediction
  • Collaborate with interdisciplinary teams of lab scientists, program managers, and software engineers to define research objectives and translate findings into practical applications
  • Manage and prioritize multiple research projects, ensuring alignment with Absci's goals and timelines
  • Contribute to the architectural design of AI systems, balancing research exploration with production-grade implementations
  • Provide thought leadership for the team, particularly in methods relevant to antibody engineering
  • Mentor team members, fostering their growth as AI researchers and engineers
  • Represent Absci's AI research capabilities at conferences, in publications, and in collaborations with academic and industry partners
  • Instilling and ensuring adherence to the company's core values

AbSci improves protein expression and biomanufacturing in the biotech industry with its advanced protein expression platform, which uses a semi-oxidizing cytoplasm and a dual inducible promoter system for precise control over protein production. Its standout product, SoluPure, is a chromatography-free purification method that simplifies and speeds up the protein purification process. AbSci sets itself apart from competitors by offering proprietary technologies that enhance drug discovery and manufacturing, aiming to replace traditional mammalian expression platforms. The company's goal is to streamline the production of biologics, transforming the biopharmaceutical industry.

Company Stage

IPO

Total Funding

$221.7M

Headquarters

Vancouver, Washington

Founded

2011

Growth & Insights
Headcount

6 month growth

3%

1 year growth

0%

2 year growth

-8%
Simplify Jobs

Simplify's Take

What believers are saying

  • Absci's AI platform achieved breakthroughs in de novo antibody design for HIV.
  • Partnerships with MSK and AstraZeneca expand Absci's drug discovery capabilities.
  • Recent $86M stock offering strengthens Absci's financial position for future growth.

What critics are saying

  • Integration issues with Twist Bioscience may delay antibody discovery projects.
  • High expectations from MSK partnership could impact Absci's reputation if unmet.
  • Rapid pipeline expansion may strain resources and lead to inefficiencies.

What makes Absci unique

  • Absci uses AI and synthetic biology for novel protein-based drug discovery.
  • Their SoluPure method simplifies protein purification, reducing production time and costs.
  • Absci's platform integrates drug target identification, candidate discovery, and cell line generation.

Help us improve and share your feedback! Did you find this helpful?

INACTIVE