Bioinformatics Scientist

Menlo Park, CA
Introduction to Aether

Aether was founded under the belief that synthetic biology will fundamentally change the future of manufacturing. In order to catalyze the next industrial revolution, we are building a fully automated robotic laboratory that will generate enough data to leverage deep learning for biological engineering for the very first time. To do this, we are building a diverse team of software engineers, machine learning engineers, process engineers, roboticists, bioengineers, environmentalists, sci-fi nerds, and world-changers. We hope you can join us.

Job Description

The revolution in enzyme engineering will leverage the state-of-the-art in analysis, modeling, and general understanding of enzymes and enzyme sequences. New machine learning based approaches, which will be built on top of datasets of enzyme/compound reactivity unparalleled in both size and quality will complement the existing frameworks. To build datasets representative of the entire spectrum of possible enzyme catalytic activity, we will need to design exploration strategies around known sequence-based enzymatic features, ensure the data generated is at a standard of quality that is high-enough, and free of any bias or confounder, to be ingested towards black-box machine learning techniques.

Enzyme science is a pillar of expertise required to realize Aether’s vision. We are looking for experts to help us drive the overarching enzyme engineering activities of the company. Over time, we expect to develop new and powerful insights into enzymes sciences by using modern analytical tools applied on the world’s largest database of enzyme / compound reactivity: our own. Said insights will be leveraged to rethink enzyme classification, our collective understanding of the general capabilities of enzymes, to open up entirely new catalytic areas for industrial applications, optimize multi-level screening strategies, and leverage our hyper-throughput robotic systems to change the available paradigm for enzyme evolution.
As an early member of the bioinformatics team, you will lead the charge to develop next-generation solutions to manage and select enzymes for high-throughput screening. You will be ultimately responsible for the quality of results achieved on the enzymes selected for any given application. You will partner with other experts within Aether Biomachines to shape the long term vision of the organization, and be empowered to ensure that progress in the enzyme sciences side of the organization is moving at a pace consistent with overall success of our endeavors. You will interface heavily with the other technology groups: machine learning, process engineering and automation, software engineering, analytical sciences, wetlab protein sciences, and computational chemistry. You will use your strong background in bioinformatics to spearhead all computationally-driven enzyme work within Aether Biomachines.
You will help grow a fast-paced, high-output band of scientists, hackers, and builders, and play a critical role in shaping the scientific environment in which the bioinformatics and general technology groups will execute.
You will work daily with industry and thought leaders in laboratory automation, chemical manufacturing, etc. Through hard work and dedication, you will power the creation of the most advanced factory supporting a revolution in chemical manufacturing.

Job Responsibilities

As a member of the scientific staff within Aether, you will play a key role in shaping the scientific culture, building world class scientific solutions and evangelizing the scientific approach across the organization. Core responsibilities include:

Work closely with other team members within the computational chemistry, machine learning and software engineering groups to design and implement exquisite algorithms and processes for next generation screening of enzymatic activities. Ultimately be accountable for furthering the fundamental understanding of enzymes and their function within Aether Biomachines.

Continuously assess state-of-the-art algorithms in enzyme homology modeling, enzyme / compound binding and reactivity, as well as select, onboard and refine the most appropriate ones to support the long term vision of the company

Develop novel and groundbreaking heuristics and models to assess enzyme similarity, as well as the design of mutagenesis libraries

Develop protocols, statistical models and algorithms to guarantee the experimental data quality is free of process issues and representative
of the true underlying catalytic activity of enzymes

Select the meta-data that should be tracked to fully annotate the experiments run in the lab

Be a key contributor to the collective braintrust to decrease the number of physical experiments that need to be run to achieve a given business or R&D objective

Formalize the internal ontology of enzymes best relevant to enzyme catalytic activity. Maintain it in our databases by working closely with the engineering teams

Work very closely with the analytical sciences and machine learning teams to:
- Develop techniques, predictive models, and run experiments to ensure compatibility of the enzymes selected with the challenges being tackles and the available measurement tools
- Develop tools to analyze lab data outputs to ensure its quality and representativity with respect to expectations 

Work very closely with the software engineering and machines learning team to:
- Educate on enzymatic and catalytic data quality
- Ensure the compatibility between the data being acquired and the models being developed
- Assess potential confounders in biochemical experimentation that could impact classifier performance
- Operationalize predictive and Quality Control algorithm for 24/7 operation and use in the robotic laboratory

Work very closely with the operations team to:
- Maximize the value of data being acquired by developing quality control and verification protocols
- Develop appropriate QC metrics and acceptability protocols
- Review, analyze, and ensure the organization is learning from samples that fail processing QC
- Troubleshoot operational data

Bring a can-do attitude to solve new and challenging problems in a fast-paced environment

Be a key stakeholder and team player in building an industry leading scientific team

Participate from the inside in the development of a high growth startup

Perform other related duties as assigned and based on Company needs

Minimum Requirements

    • Ph.D. in bioinformatics, biophysics, biochemistry, biology, computational chemistry, computer science, computational modeling, computational biology, or equivalent combination of education and experience to perform independently at this level
    • 5 years of experience as a computational scientist or bioinformatician directly implicated with enzymatic screening, enzyme evolution, or high-throughput enzyme-related activities
    • Proficient in statistics and able to apply it to experimental design and analysis
    • Working knowledge of state-of-the-art bioinformatics, computational biology, and protein/small molecules modeling tools
    • Experience in modeling, de novo prediction, structure visualization and analysis, docking, molecular dynamics, and structure-based protein/small molecules
    • Programming experience in Perl, Python, R and working knowledge of Rosetta or similar computational packages
    • Experience and proven expertise in analysis of large datasets
    • Functional knowledge of mass spectrometry data, in particular TOF and TOF/TOF
    • Expert knowledge of chemistry, organic chemistry, and biochemistry
    • Excellent verbal and written communication skills
    • Proficiency with productivity software
    • Experience with creating drawings, flow charts, process diagrams, BOMs, product specifications, SOPs and other documentation

Preferred Requirements

    • 2 years of experience with Laser Desorption / Ionization-based, TOF Mass Spectrometry
    • Experience developing distributed software systems
    • Experience scaling up computational capabilities of systems
    • Experience with NGS library sample preparation and instrumentation, eg. MiSeq is a plus
    • Experience designing, building, implementing, or validating predictive computational systems
    • Experience selecting, designing, building, programming, or using robotic systems tailored for ultra high throughput screening of small molecule assays
    • Experience in rapidly growing start-ups
    • People management / hiring experience
    • Project management experience
    • Experience using Quality Management Systems