Machine Learning Platform Engineer

Panakeia is the world's first in silico multi-omics company, building AI solutions that power precision medicine in clinical settings,  platform also accelerates drug discovery and development for the medicines of tomorrow.

Our PANProfiler platform uses a biology-first AI approach to determine biomarker status across DNA, RNA, proteins, and metabolites directly from routine brightfield images of cells and tissues — no specialist equipment required. Two UKCA-marked clinical products derived from the platform are already deployed in hospitals across the UK and worldwide, giving clinicians faster, more accessible diagnostic insights to inform the treatment decisions that matter most.

The platform has been independently validated in peer-reviewed publications including Nature Communications Medicine, where it was recognised as one of the journal's top 25 papers of 2024, and results have been presented at leading clinical conferences including ESMO, ASCO, and AACR. We work closely with regulators — including the MHRA and FDA — to set the standard for safe, clinically-validated AI in healthcare.

Our fast-growing, multi-disciplinary team spans AI, molecular biology, and clinical science. If you're excited by technology that reaches patients directly and shapes how medicine is practised, this is where that work happens.

As an ML Platform Engineer at Panakeia, you will sit at the critical junction of research, engineering and product delivery. You will be responsible for designing, implementing and maintaining our multi-omics platform architecture, building and validating data and machine learning pipelines. This role requires a blend of analytical thinking, architectural engineering capability, and the ability to communicate complex findings to both technical and executive stakeholders.

• Design, implement and evolve a multi-omics AI platform, incorporating full-lifecycle MLOps
• Identify, ingest, link and curate data across large-scale multi-omics and imaging datasets, including data quality, validation, traceability and storage optimisation
• Standardise and automate the model lifecycle, so research models can move into production with confidence
• Build and orchestrate analytical/processing pipelines across ingestion, training, inference and post-processing with built-in monitoring and observability
• Design and implement processes to increase efficiency in your work streams
• Identify and integrate tooling (including AI tools) to streamline your work
• Work closely with cross-functional teams (Product, Research, Engineering) to deliver high quality products
• Communicate complex technical data and experimental results to technical teams and executive stakeholders in an easy to understand way
• Operate with a high degree of independence. Prioritise competing work streams and identifying bottlenecks to ensure consistent delivery.

• Bachelor’s or Master’s degree in Mathematics, Statistics, Data Science, Computer Science, Engineering, or a related field (or equivalent practical experience).
• 2+ years of relevant industry experience in a fast-paced environment, preferably a startup, with the ability to iterate, experiment, and deliver solutions efficiently.
• Practical experience across the entire MLOps lifecycle for cloud, hybrid and on-premise deployments.
• Adaptability and comfort working with evolving requirements and changing priorities, approaching new challenges with curiosity and openness.
• Proactive, problem-solving mindset with a sense of ownership, able to spot opportunities for improvement and help move projects forward from idea to implementation.
• Strong programming experience with proficiency in Python for building and maintaining data processing, analytics, and pipeline orchestration.
• Proficiency in managing and processing large-scale, high-dimensional datasets, ensuring efficient data loading and manipulation within training pipelines, and overseeing data quality and storage optimisation.
• Familiarity with deep learning frameworks (e.g., PyTorch).
• Architecting and building an ML platform and core ML infrastructure from the ground up, ideally in a…