Machine Learning Data Scientist Cambridge, East of England, England
Job description
VACANCY – MACHINE LEARNING DATA SCIENTIST
Enhanc3D Genomics is a functional genomics spinout company from the Babraham Institute (Cambridge, UK) leveraging a disruptive technology to profile three-dimensional (3D) genome folding at high resolution.
Enhanc3D Genomics is an innovative and dynamic company with diverse and highly engaged staff. We believe in fostering great teamwork to maximise our collective skills and experience. We are passionate about realising the power of 3D genomics by developing new cutting-edge technologies for therapeutic discoveries.
Role Profile
We are looking for a forward thinking, enthusiastic, highly motivated data scientist with a strong machine learning background.
You should be an organised professional with exceptional interpersonal and communication skills, enabling you to successfully operate in a business environment where confidentiality and discretion are paramount.
Key Accountabilities
-
Lead on developing machine learning approaches to support a variety of EGs R&D use cases
- Conduct data science and investigative analysis to support EG's R&D programmes
- Work with wet-lab scientists during experimental design and analysis phases, including understanding their goals, providing statistical support, and assisting with visualisation of complex and large datasets
- Produce professional reporting outputs for internal research and external collaborations
- Work across teams and proactively engage in knowledge sharing and peer support, including training
Required Skills and Abilities
- Experience and strong knowledge of Machine Learning / Deep Learning, SciML (Scientific Machine Learning)
- Ability to deliver quick wins alongside implementing more advanced modelling techniques
- Excellent knowledge of two of Julia, Python and R. Proficient with common data science libraries/toolkits such as Julia data science libraries, Pandas, SciKit-Learn, Numpy, Keras, Tensorflow, PyTorch etc.
- Algorithm design and development, data processing, statistical analysis and visualisation of complex and large datasets
- Familiarity with common bioinformatic databases and tools
- Good knowledge of biomarker discovery / target discovery
- Knowledge of version control and collaborating with developers using GitHub
- Track record of research in bioinformatics, biostatistics and genomics
- Knowledge and ability to process, analyse and interpret NGS data across a variety of OMICS technologie
- Excellent oral and written communication skills
- Excellent organizational and record keeping skill
Desired Qualifications and Experience
- Experience with and understanding of Hi-C, capture Hi-C, HiChIP
- Experience with variant calling, exome/WGS pipelines or other high-throughput genomics workflows
- Experience of working in a fast-paced research-driven commercial environment or in collaboration with industry
- A strategic, inquisitive and innovative mindset with the ability to sense commercial opportunities in our data and exploit accordingly
- Delivery skills with the ability to work well under pressure in an agile environment
- Experience with pipeline development and software virtualisation (e.g. docker, singularity)
