Machine Learning Bioinformatics Scientist

Fulgent Genetics
Bioinformatics
United StatesCaliforniaEl Monte (Optional Remote)
www.paycomonline.net/v4/ats/web.php/jobs/ViewJobDetails?job=74121&clientkey=E86D60EDAF14F62BD0B3F719F912C645

Description

ABOUT FULGENT:

Fulgent is a leader in genetic and genomic clinical testing, a publicly traded company located in Los Angeles, California. We are a technology-driven company with extensive academic/clinical experience and capabilities in Next Generation Sequencing (NGS) and bioinformatics. This distinction has advanced us to the forefront of the rapidly advancing genetic and genomic testing industry. Fulgent's unique chemistries and superior proprietary bioinformatics pipelines have propelled our explosive growth in recent years. We offer the most expansive set of clinical genetic tests in the world, including 22,000+ single gene tests, 900+ preset panels, rearrangement testing, clinical exome/trios, whole exome/trios, whole genome and our All-in-One reflex test. We are a CLIA and CAP accredited laboratory. Fulgent has state-of-the-art clinical, sequencing and bioinformatics tools, including the latest Illumina sequencers such as the NovaSeq.

SUMMARY OF POSITION:

As a Machine Learning Bioinformatics Scientist I, you will utilize Fulgents genetic data from DNA, RNA, IHC, and other assays to predict drug response, clinical outcome,
immunotherapy efficacy, tissue of origin, expression signatures and mutation profiles. You will be expected to utilize the latest python-based machine learning classifiers, two-class and multi-class. A background in python coding and python AI packages is required, domain knowledge of immunology, genetics and NGS is desired but not essential. Ability to query relational databases is a must, as is design of well thought-out validation strategies. You will work independently in train/test strategies for your models, but work with the pipeline team to implement your final design. You will also be assigned leadership roles in projects with mentor responsibility to junior members of the team. You will strive to maximize efficiency, quality, reliability and customer usability and satisfaction.

KEY JOB ELEMENTS:

Research and Development
Download and implement tools in Scikit-Learn and SciPy.
Knowledge and some experience with Googles tensorflow.
Work independently to define, prioritize and complete objectives to meet company goals.
Work with pipeline team to implement new machine learning predictors in a commercial environment.
Write SOPs for new or updated AI-based pipeline components, or new pipelines.
Write specifications for implementation by software developers.
Production and Customer Support
Work with investigators on clinical predictors, outcome, survival, using NGS-based tools.
Review requests for new predictors, work with inside and outside-Fulgent clients to create new or optimize existing classifiers and add features according to requests
Oversee sequencing service projects, ensuring timely processing, quality results and client satisfaction.
Support software and LIMS developers in automation efforts.
Perform specialized analyses as needed for specific projects.
Keep up-to-date with current best practices and emerging methods.
Treat data with a high level of integrity and ethics.

Data Maintenance
Assist DBAs and BIFX personnel find appropriate datasets used for test/training purposes.
Aid DBAs in sequestering selected data for validation purposes.
Write reports detailing validation/update methodology and results.

Validation
Develop procedures for training, testing and validating machine learning predictors.
Document and maintain data used for training and testing and validation.
Write validation reports detailing validation methodology and results.


Qualifications

Ph.D. degree from an accredited institution in Bioinformatics, Machine Learning, or computer science/software engineering.

Demonstrated knowledge of Fulgent specific methods and processes.

Experience analyzing DNA and RNA NGS data.

Expertise with statistics for big data analysis and multiomics.

Expert level hands-on skills in databases and database access.

Expert level in relevant programming languages, preferably python and/or Java.

Must enjoy working in a multi-disciplinary and collaborative environment.

Ability to troubleshoot both individually and as part of a team.

Excellent oral and written skills with the ability to communicate in an open, transparent, timelyand consistent manner.

Experience in team software development and integration projects is a plus.


Start date

As soon as possible

How to Apply

Apply directly using the provided URL or contact recruiter Deanna Tremblay for more information.


Contact

Deanna Tremblay
dtremblay@fulgentgenetics.com