Data scientist at deep learning/AIRR-seq startup


Hi AIRR-folk,

I am recruiting for a brand new startup based in the UK that is working to apply deep learning methods to antibody repertoire data to discover new drugs. We are looking for a computational person with AIRR-seq experience to work on our core platform and do data analysis. Job description follows. Please reach out to me directly if you are interested: uri [at]

The Company

Alchemab Therapeutics is an exciting, big ambition, fast-paced therapeutics newco. The company brings together cutting-edge technologies including antibody repertoire profiling and deep learning and world-leading expert founders and management team.

Alchemab aims to deliver a pipeline of targets and therapeutic candidates over the next 18 months. Beyond this, Alchemab aims to be a transformational large and small molecule therapeutics company with a broad pipeline of internal and partnered novel targets & candidates. The company is currently based in London, but with research activity ongoing in Oxford and Cambridge.

The Role

The Data Scientist will work alongside the scientific team and will have a foundational role in building Alchemab’s platform. They will work closely with Alchemab’s founders and collaborators to build core components of the end-to-end data pipeline, establishing standards and practices. The Data Scientist will be involved in patient stratification and management, analysis and visualisation of large scale omics data. They will work within a virtual team to support target identification. As the company grows, the Data Scientist will support the scientific leadership team to build, further coordinate and establish Alchemab’s technology platform & team. The Data Scientist will report to the Chief Technology Officer (CTO).


  • Perform analysis of human disease datasets, for example, large-scale omics datasets including antibody/B cell receptor sequencing, RNAseq and single cell sequencing
  • Develop computational models to stratify patient groups, evaluate antibody repertoires and enable data-driven target discovery
  • Support team to build and maintain a secure data pipeline
  • Advise on and support activities to functionally validate targets using in silico approaches (e.g., FGWAS, GWAS)
  • Work collaboratively with the team including Data Science research groups and external partners in Oxford, Cambridge, and elsewhere
  • Communicate efficiently, interpret, summarise and visualise data for presentation to different audiences
  • Keep current on new discoveries and changes in methodologies and approaches that might enhance Alchemab’s platform
  • Work closely with the scientific leadership team to help build Alchemab’s platform and team

Experience & Requirements


  • A PhD (or in exceptional cases, a masters level degree) in computer science, bioinformatics or related discipline or similar
  • Experience at working with large-scale genomic or functional genomic datasets
  • Proficient with Python and/or R
  • Mastery in integrating and analysing diverse high-dimensional omics data sets relevant for immunology, oncology, neuroscience, or others therapeutically-relevant fields
  • Experience in building infrastructure for large scale data analysis and storage
  • An ambition to work with the Alchemab team to build a transformative company
  • A team player who proactively and directly communicates and collaborates with other team members


  • Expertise in working with AIRR-seq data
  • 5+ years of industry experience
  • Pre-existing network of external scientific contacts of relevance to Alchemab
  • Evidence of contribution to and influence of the strategic scientific direction of a large group