The Team You’ll Join 

As part of Recursion's Value Tech Tooling Team, you will be at the forefront of reimagining drug discovery from first principles using our massive data capabilities. You'll work in a cross-functional team of world-class computational biologists and engineers who turn complex analyses and data workflows into stable tools and pipelines that multiply their impact and industrialise the discovery process across a wide array of therapeutic areas. You'll partner with biologists, medicinal chemists, engineers, data scientists, ML scientists, and to design experiments, develop new methods, build scalable data workflows, analyse results, and identify common themes across programs. As our toolbox grows and evolves, it will contribute to a revolution in drug discovery to bring life-changing therapeutics to patients at greater speed and with higher quality, safety and efficacy than ever before.

In this role, you will:

• Synthesize, integrate, and analyse diverse internal and external datasets from computational biology, target discovery, functional genomics, biomarker discovery, and real-world and clinically derived data sources, and identify commonalities to turn into reusable tools and pipelines.
• Build, maintain, and improve robust data pipelines and analytical workflows for complex biological datasets, including omics data, internally generated biological assay data, and external data sources such as Tempus and other real-world datasets.
• Develop and apply agentic workflows to integrate and orchestrate analyses across multiple internal and external data sources, accelerating insight generation and supporting scalable decision-making across drug discovery programs.
• Partner with engineers to mature pilot tooling and workflows into stable products and infrastructure that multiply the effectiveness of scientific collaborators pursuing drug programs.
• Present and discuss data, pipelines, and tools with decision makers and stakeholders in a clear and compelling way that drives toward getting medicines to patients.
• Collaborate cross-functionally with Recursion’s platform data science, data engineering, and ML teams to further advance Recursion’s ability to interpret and translate large-scale phenomics and multimodal data into therapeutic programs.

The Experience You’ll Need

• PhD in a relevant field (e.g., computational biology, bioinformatics, statistics, quantitative pharmacology, cancer/cell biology, computer science, or a related discipline), or equivalent experience, with a track record of applying these skills to fundamental problems in drug discovery.
• Experience applying computational methods (including statistical, probabilistic, and/or machine learning techniques) to analyse complex biological and/or human clinical data.
• Experience building, maintaining, and improving reproducible data pipelines and analytical workflows for large, heterogeneous biological datasets (Python strongly preferred).
• Experience working with high-dimensional biological datasets, including omics data (e.g., single-cell and other genomics-based modalities) and/or other complex assay modalities.
• Experience turning exploratory analyses into reusable tools, workflows, and documentation that can be adopted by other scientists/teams.
• General understanding of drug discovery and translational biology.

Nice To Have

• Experience working on highly collaborative cross-functional teams; ability to clearly explain computational analyses, data workflows, and methodologies to cross-functional and non-technical teams.
• Hands-on experience working with real-world clinical datasets (EHR/claims/registries) and/or generating real-world evidence (cohorting, endpoint definition, observational study considerations).
• Experience with real-world clinical datasets (e.g., EHR-derived oncology datasets) or demonstrated ability to rapidly learn new healthcare data modalities; experience with Tempus or similar datasets is a plus.
• Experience integrating multimodal datasets (e.g., genomics + phenomics, genomics + imaging) in service of translational decisions.
• Experience developing or applying agentic workflows to orchestrate analyses across multiple internal and external data sources, accelerating insight generation and decision-making

Working Location & Compensation:

This is an office-based, hybrid position at our office located in London, England. Employees are expected to work in the office at least 50% of the time.

At Recursion, we believe that every employee should be compensated fairly. Based on the skill and level of experience required for this role, the estimated current annual base range for this role is £86,300 - £115,500. You will also be eligible for an annual bonus and equity compensation, as well as a comprehensive benefits package. 

#LI-EP1

The Impact You’ll Make

As a key member of Recursion's partnership-facing data science team, you will be at the forefront of reimagining drug discovery from first principles using Recursion’s massive data and compute capabilities. As senior computational biologist, you will be supporting a portfolio of partnership preclinical drug programs and be responsible for designing and executing analyses to support target nomination, validation, and early programs in neuroscience diseases.

You will integrate layers of Recursion platform data (phenomics, transcriptomics, proteomics, etc) to validate the link between target and disease biology and to propose targets and early programs in novel areas of neuroscience. You will partner with biologists and medicinal chemists to build supporting data packets for targets from our phenomic maps, target screens, and partnered patient data sets. You will also collaborate with computational scientists from across the organization to develop, deploy, and scale novel approaches to: 1) translational validation in hit to lead, 2) mechanism-of-action identification/de-risking, and 3) build evidence for patient connectivity to match the targets we are validating and medicines we are creating to the patients who need them.  

In this role, you will:

• Deliver biological insights on therapeutic candidates and disease biology from the analysis of high-dimensional (phenomics, transcriptomics, proteomics, patient-derived) datasets that support clinical development planning
• Evaluate the biological and molecular evidence for therapeutic hypotheses and accelerate drug program progression into the clinic
• Synthesize diverse datasets (internal and external) to generate and evaluate hypotheses for drug discovery, biomarker development, mechanism of action and target population identification
• Present data analysis to decision makers and stakeholders in a clear and compelling way that drives toward getting medicines to patients
• Assess new data sources, develop and scale new analysis methods, and support key program decisions with the ultimate goal of bringing life-changing therapies to patients at unprecedented speed
• Industrialize analysis approaches to not only solve for the current project, but also to accelerate future projects and scale the impact that we can have
• Collaborate cross-functionally with Recursion’s data science, biology, medicinal chemistry, and  platform, teams to further advance Recursion’s ability to interpret and translate large-scale data assets into therapeutic programs

The Team You’ll Join 

Our group is a bold, agile, diverse collective of computational drug discovery scientists and data scientists deeply focused on the singular goal of bringing new therapeutics into the clinic at an accelerated pace. We are a computational group that spans precision oncology, neuroscience, and I&I (immunology and inflammation), and focuses on advancing novel, targeted therapies for these disease areas. We partner closely with our biologists and medicinal chemists to design and execute impactful and decisional data analysis for multiple programs. We are responsible for data strategy across the portfolio and supported by computational leadership in designing scalable and reproducible experiments that serve to advance multiple programs within the portfolio. 

Our team collaborates extensively with computational biologists in other therapeutic areas (immunology, oncology, etc.) as well as data scientists and engineers from our core platform teams to provide a strong network of feedback and support. 

The Experience You’ll Need

• PhD in a relevant field (computational biology, systems biology, bioinformatics, neuroscience, etc.) with a very strong computational focus and 5+ years of experience in biotech or pharma industry OR MS in a relevant field
• Experience applying computational methods (including probabilistic, statistical, and/or machine learning techniques) to analyze and integrate matched human clinical and molecular data in a high-level programming language such as Python or R
• Deep expertise in the analysis and data integration of one or more ‘omics data modalities (phenomics, transcriptomics, proteomics, genomics) and/or human clinical data
• Exceptional data visualization skills
• Excellent cross-functional communication skills, including an ability to explain complex scientific concepts to a variety of audiences using a combination of plots, documents, and presentations

Nice To Have:

• Strong understanding of patient genetics and historical druggability of disease-relevant pathways,  including experience working with patient data
• Experience in efficiently advancing drug programs from proof of concept and into clinical development
• Experience with neuroscience clinical trial biomarker analysis
• Experience working as part of partnerships or client facing (consulting) teams

Working Location & Compensation:

This is an office-based, hybrid role in either our Salt Lake City or New York City offices. Employees are expected to work in the office at least 50% of the time.

At Recursion, we believe that every employee should be compensated fairly. Based on the skill and level of experience required for this role, the estimated current annual base range for this role is $200,600 to $253,100. You will also be eligible for an annual bonus and equity compensation, as well as a comprehensive benefits package. 

#LI-EP1

Research Scientist - Applied Large Language Models 

Your impact 

As a Research Scientist focused on the application of Large Language Models (LLMs), you will play an exciting role in bringing cutting edge technologies to bear across our research areas to transform the drug discovery world as we know it. 

Working in a highly creative, fast-paced and interdisciplinary environment, you will be partnering with leading research scientists and engineers to conceive, design, and develop cutting edge LLM applications that help to unlock new modelling capabilities and predictive power which will be critical to the organisation’s success. You will draw upon your existing deep understanding and experience whilst learning from those around you, to apply novel techniques and ideas to newly encountered computational biology and chemistry problems.

Depending on your experience:

You will both partner with teams across our existing research areas and create and lead standalone projects, bringing together a variety of disciplined scientists and engineers to pursue some of the most ambitious modelling problems through the application of LLMs - as well as providing technical mentorship and people management for others in the ML community at Isomorphic Labs.

You will be instrumental in leading machine learning based research projects, building the models, and algorithms that will power our platform to drive us close to achieving our ambitious mission to one day solve all disease with the help of AI.

What you will do

• Contribute to core research in machine learning by pushing the boundaries of Large Language Models in their application to the world of drug discovery
• Develop and refine LLM-driven approaches for multiple use cases across our research areas, using your extensive knowledge of the field to modify and apply models and explore their capabilities when applied to complex biological and medical challenges.
• Identify and create novel ML techniques and the required data to train and apply models
• Analyse and tune experimental results to inform future experimental directions.
• Implement and scale training and inference engineering frameworks
• Report and present research findings and developments clearly and efficiently, to both other ML scientists and scientists of different disciplines
• Iterate collaboratively with scientists and domain experts, sharing your own domain experience
• Suggest and engage in team collaborations to meet ambitious research goals
  
  Depending on your experience:
• Provide technical mentorship and guidance to the ML research community, advising on projects, and shaping our research roadmap based on your deep technical expertise.
• Provide developmental support to other ML research scientists.
• Create, lead, and run ML research projects, fostering collaborative and diverse teams to solve high priority modelling problems. Cultivate a diverse and inclusive research culture.

Skills and qualifications 

Essential

• PhD or equivalent practical experience in a technical field
• Highly specialized LLM builder with a passion for, and strong experience in, applying LLMs to novel problem spaces
• Deep understanding and experience of model architectures, training methods, and techniques for application of LLMs, including deployment for bespoke use cases and applications, established experience in post-training, reasoning, test-time scaling, tool-use, alignment, agents, LLM research, as well as reinforcement learning and fine-tuning 
• Strong knowledge of linear algebra, calculus and statistics.
• Experience using ML frameworks such as JAX, PyTorch, or TensorFlow, and scientific software such as NumPy, SciPy, or Pandas.
• Depending on your experience: project supervision, leadership, or management.
• Strong knowledge of LLM landscape today, and likely developments for the near future
• Experience working with real-world datasets.

Nice to have

• PhD in machine learning or computer science.
• Relevant research experience to the position such as post doctoral roles, a proven track record of publications, or contributions to machine learning codebases.
• A strong background in biology or medicine, enabling you to bridge the gap between advanced AI capabilities and complex scientific problems in drug discovery
• Experience working in a scientific environment across disciplines (particularly biology, chemistry, physics), and with real world biological or chemical datasets and biological or chemistry software
• Experience in computational chemistry, bioinformatics, or related fields would be highly beneficial, along with a track record of applying AI to real-world scientific challenges
• Experience with multi-parameter optimization
• Experience in any of: large scale deep learning, generative models, graph neural networks, deep learning for drug discovery, deep learning for computer vision, 3D graphics/robotics, real-world applied RL

About the role

We are looking for a meticulous and detail-oriented Biology Data Quality Engineer to ensure the integrity and usability of the various and complex datasets that are central to our mission. In this critical role, you'll leverage your expertise in biology, data science, and machine learning to ensure the quality and consistency of biological data used to train and evaluate our foundation models. You'll work in collaboration with the R&D team and our engineers, using your skills to ensure our data meets the highest standards.

What you'll be doing

As a Biology Data Quality Engineer, you will own the following tasks:

• Data Validation Pipeline Development: Develop and implement comprehensive data validation protocols for diverse biological datasets (histology, omics, clinical). Ensure data integrity, consistency, and accuracy through rigorous quality checks. Design and implement automated data quality pipelines to streamline data validation and identify potential issues early in the data processing workflow.
• Data Curation & Standardization: Establish and enforce data standardization practices to facilitate seamless integration and analysis across different data types. Curate datasets to enhance their usability for machine learning.
• Collaboration & Communication: Work closely with the R&D team to understand data requirements and address data quality concerns. Communicate data quality findings and recommendations effectively to technical and non-technical stakeholders. Communicate and synchronize with external data providers.
• Documentation & Reporting: Maintain a detailed documentation of the data-quality assessment procedures, validation results, and data specifications. Generate regular reports on data quality metrics and trends.
• Data Source Evaluation: Evaluate and validate external public data sources, ensuring they meet our quality standards and are suitable for inclusion in our foundation model training.
• Continuous Improvement: Stay up-to-date with the latest data quality best practices and tools in the biological domain. Propose and implement improvements to our data- quality assessment processes and pipelines.

What you'll bring

The successful candidate will have a ‘team-first’ kind of attitude; be independent, curious, and detail-oriented; thrive in a dynamic, fast-paced environment; and be fun to work with. We value individuals who bring strong domain expertise in biology alongside strong computational, hands-on skills.

• Omics Data Expertise. Deep understanding of transcriptomics data types (bulk, single-cell, spatial) and their specific quality considerations. Good knowledge of genomics and proteomics data.
• Data Quality Management: Proven experience in implementing data quality control procedures and pipelines. Familiarity with data validation tools and techniques.
• Analytical Skills: Strong analytical and problem-solving skills to identify and resolve data quality issues.
• Programming & Data Analysis: Proficiency in Python, good knowledge of data visualization libraries (e.g. matplotlib).
• Communication Skills: Excellent written and verbal communication skills to effectively convey data quality findings and recommendations.
• Educational Background: MSc in Biology, Computational Biology, Bioinformatics.

How to stand out:

• Computational Pathology Data Expertise: Experience in machine learning analysis of histology images.
• Cloud expertise: Experience working with AWS.
• Data Annotation Experience: Experience with developing and implementing data annotation guidelines and processes. Experience with data ontologies.
• Proven experience building or contributing to large-scale data collections (e.g. Human Cell Atlas).
• Spatial alignment of multimodal datasets (e.g. alignment between different imaging modalities)

The candidate journey

To be considered, please submit your CV in English. We believe in a transparent and collaborative interview process. Here is what you can expect after submitting your application:

1. Screening: Once you have applied, the hiring team will review your application to determine if your work experience and skills align with the necessary proficiencies of this position.
2. Technical Assessment: Given the technical nature of the role, you will be invited to complete a timed (up to 1 hour and 30 minutes) technical assessment on a dedicated platform. This stage consists of a short set of Python exercises designed to assess your coding proficiency.
3. Interviews:
   • Hiring Manager (30 min): A call with the Hiring Manager to discuss your background, motivation, and expertise. This will include a deep dive into your technical skills, including your experience with coding and cloud environments.
   • Data Curation Project (Take-home): Based on the outcome of the previous call, you will be assigned a Data Curation homework. This assignment covers one or more key data modalities and consists of the submission of Python code and a detailed report about your work.
   • Assignment Presentation & Technical Q&A (60 min): You will present your take-home assignment to a broader team. You are also welcome to include a brief presentation of your past experience. This session consists of a 30-minute presentation followed by a 30-minute Q&A to discuss your homework and probe your deeper technical expertise.
   • Executive Interview (30 min): A comprehensive discussion with our Senior Leadership. This session moves beyond technical competency to focus on long-term vision, values, and mutual potential.
4. Offer: Following the completion of the interviews, our hiring team will make a final decision and will be in touch to share the outcome of your interviews. If the team would like to move forward, the recruiter will discuss the details of our proposed offer with you.
5. Onboarding: We are happy to have you joining the team. Once you have accepted and signed your offer, we will be in touch to begin the process of onboarding you to Bioptimus.

Why This is a Unique Opportunity

You will:

• Be part of a trailblazing team working at the intersection of AI, biotech, and biomedical research.
• Take on a high-impact leadership role, shaping the future of biomedical AI through strategic data partnerships.
• Work in a collaborative, innovation-driven environment with top researchers and industry experts.

And benefit from:

• A collaborative and mission-driven work environment.
• Competitive salary and equity package.
• Flexible work arrangements, including remote options.
• Opportunities for professional growth and leadership development.
• Shape the future of biology and AI by contributing to groundbreaking work.