Job:Senior Scientist, Applied Machine Learning @ CITRE (Seville, Spain)
0
0
Entering edit mode
6 weeks ago

At Bristol Myers Squibb, we are inspired by a single vision – transforming patients’ lives through science. In oncology, hematology, immunology and cardiovascular disease – and one of the most diverse and promising pipelines in the industry – each of our passionate colleagues contribute to innovations that drive meaningful change. We bring a human touch to every treatment we pioneer. Join us and make a difference.

Within the Predictive Sciences team at CITRE (Seville, Spain), we seek enthusiastic and exceptional candidates for a senior scientist position with a demonstrated research background in machine learning, a track record of independent research, experience in creatively solving technical problems, and a proven ability to deliver prototype predictive models based on the latest published research.

CITRE is Bristol Myers Squibb’s research institute in Europe, and our link to the European research community. Informatics & Predictive Sciences at CITRE performs innovative computational research to inform decisions across all stages of drug development. Areas of research include computational and network biology, machine/deep learning, cheminformatics, predictive modeling, patient stratification, and method development for analysis and interpretation of biological data.

The candidate will work as part of a multidisciplinary team focused on rational design of novel therapeutic modalities. She/he will be able to perform pioneering and impactful research alongside very collaborative computational and experimental scientists, with expertise in ML, structural biology, chemistry, cell and gene therapy. We encourage inquiries from those with a background in AI/ML who also have an interest in innovation and interdisciplinary application of computational approaches to life sciences data.

The Role

Participate in our growing effort to apply cutting-edge AI/ML techniques towards the development of novel therapies to treat cancer and hematological malignancies.

  • Collaborate closely with teams across the company to solve complex problems, including design and implementation of computer vision, time-series forecasting, geometric deep learning and/or reinforcement learning models.
  • Refine ML models and workflows by performing exploratory data analysis on large datasets.
  • Creatively propose hypotheses and test them rigorously.
  • Author scientific reports, and present methods, results, and conclusions to publishable standard.

Minimal Qualifications

  • Ph.D. with 2+ years of postdoctoral experience in Machine learning, Bioinformatics, Computational Chemistry, Electrical Engineering, Computer Science, Statistics, Applied Math, Physics, or related technical field
  • Strong experience or interest in applying contemporary deep learning methods
  • Strong publication record in relevant conferences or journals
  • Expertise in scientific programming languages (e.g., Python, R) and libraries (Pandas, Numpy, Scipy, Scikit-learn, …) and their application to mine large datasets
  • Experience with one DL framework among PyTorch, TensorFlow, and JAX.
  • Excellent verbal and written communication skills. Verbal and written English language fluency are a prerequisite.
  • Intense curiosity about the biology of disease and eagerness to contribute to scientific and computational efforts.

Nice to have

  • Experience with ML applied to bioimaging, bioinformatics problems, including single cell and spatial omics is a strong plus
  • Prior research projects in pharma/biotech, university, or hospital environments.
  • Experience managing multi-modal data (omics, imaging and time-series signals).
  • Previous experience using cloud-based computing and software engineering frameworks (e.g. Docker, Git).
Machine-Learning • 208 views
ADD COMMENT

Login before adding your answer.

Traffic: 1043 users visited in the last hour
Help About
FAQ
Access RSS
API
Stats

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.

Powered by the version 2.3.6