About this job
<h1><strong>Project Tricorder — Clinical Infrastructure for Field Operations</strong></h1><p style="min-height:1.5em">We're looking for a hands-on engineer to build two foundations of the Tricorder product: the evaluation harness and training data pipeline behind our AI models, and a clinical knowledge base grounded in tactical combat care, SNOMED CT and ICD-10.</p><p style="min-height:1.5em"></p><h2><strong>About Project Tricorder - </strong><a target="_blank" rel="noopener noreferrer nofollow" href="https://www.tricorder-systems.com/"><strong>https://www.tricorder-systems.com/</strong></a></h2><p style="min-height:1.5em">Most healthcare technology assumes a hospital: reliable power, connectivity and a clinician at a desk. Care increasingly happens somewhere else - in the field, in transit, in remote and contested environments, and in the critical minutes before a patient reaches a ward.</p><p style="min-height:1.5em"><strong>Tricorder</strong> builds the deployable clinical infrastructure for that world: a rugged, self-contained hardware and software platform that lets clinical teams capture, monitor and act on patient data anywhere, even when the network or the grid can't be relied on. It is a dual-use venture serving defence medical and civilian pre-hospital care.</p><p style="min-height:1.5em">Our prototype product is already in user testing. Edge AI sits at the core: multimodal language models that turn video, sensor data and clinical notes into patient records, drive predictions and inform data-driven learnings across deployments. To trust those models in the field, we need rigorous data and evaluation - that's where you come in.</p><p style="min-height:1.5em"></p><h2><strong>What you'll do</strong></h2><p style="min-height:1.5em">You'll own two workstreams, working day to day with the founder and the FF build team.</p><p style="min-height:1.5em"></p><h2><strong>1. Data pipeline and evaluation harness</strong></h2><p style="min-height:1.5em">Build the data foundations that tell us whether our models are good enough for clinical use.</p><ul style="min-height:1.5em"><li><p style="min-height:1.5em"><strong>Data labelling:</strong> design labelling schemas and guidelines, set up tooling, and run labelling with clinical input, including quality checks and inter-annotator agreement.</p></li><li><p style="min-height:1.5em"><strong>Data processing:</strong> build reproducible pipelines to ingest, clean, de-identify and transform multimodal data (video, sensor streams, text).</p></li><li><p style="min-height:1.5em"><strong>Video data organisation:</strong> structure, version and catalogue video datasets so clips, annotations and metadata stay searchable and traceable.</p></li><li><p style="min-height:1.5em"><strong>Training dataset preparation:</strong> assemble balanced, well-documented train, validation and test splits, with clear lineage from raw data to model input.</p></li><li><p style="min-height:1.5em"><strong>Eval harness:</strong> build an automated harness that benchmarks vision-language and NLP models against clinically meaningful metrics, tracks regressions and supports build-vs-buy model decisions.</p></li></ul><h2><strong>2. Clinical knowledge base</strong></h2><p style="min-height:1.5em">Build the structured clinical knowledge base that turns unstructured input into coded, interoperable records.</p><ul style="min-height:1.5em"><li><p style="min-height:1.5em"><strong>Database design:</strong> design the schema and stand up the data store for clinical concepts and their relationships.</p></li><li><p style="min-height:1.5em"><strong>Clinical terminologies:</strong> ingest and map TC3, SNOMED CT, ICD-10 and related NHS standards, including cross-mappings between them.</p></li><li><p style="min-height:1.5em"><strong>Natural language processing:</strong> extract entities and relationships from clinical text and link them to coded concepts.</p></li><li><p style="min-height:1.5em"><strong>Document handling:</strong> parse and structure clinical documents (PDFs, notes, forms) into the database.</p></li><li><p style="min-height:1.5em"><strong>Clinical knowledge:</strong> work with clinicians to make sure the database reflects real-world clinical reasoning and pre-hospital workflows.</p></li></ul><p style="min-height:1.5em">By the end of the first 3 months, we'd expect a working eval harness in use for model decisions, a labelled and versioned core dataset, and a first version of the knowledge base linked to the product.</p><p style="min-height:1.5em"></p><h2><strong>What we're looking for</strong></h2><p style="min-height:1.5em">We don't expect one person to be expert in everything below. Strong candidates will be deep in one workstream and credible in the other.</p><p style="min-height:1.5em"></p><h3><strong>Must-haves</strong></h3><ul style="min-height:1.5em"><li><p style="min-height:1.5em">Strong Python and data engineering skills, with a track record of shipping production data or ML pipelines, not just research notebooks.</p></li><li><p style="min-height:1.5em">Hands-on experience building ML evaluation frameworks, benchmarks or test harnesses, ideally for vision, video or language models.</p></li><li><p style="min-height:1.5em">Experience running data labelling and training-data preparation, including annotation tooling and quality control.</p></li><li><p style="min-height:1.5em">Working knowledge of databases and data modelling.</p></li><li><p style="min-height:1.5em">Practical NLP experience: entity extraction, entity linking or document parsing.</p></li><li><p style="min-height:1.5em">Comfort handling sensitive data under data protection and clinical safety constraints.</p></li><li><p style="min-height:1.5em">Pragmatism and speed: you can work with ambiguity, make good build-vs-buy calls and ship in weeks, not quarters.</p></li></ul><h3><strong>Nice to have</strong></h3><ul style="min-height:1.5em"><li><p style="min-height:1.5em">Experience with SNOMED CT, ICD-10, dm+d or other NHS clinical terminologies and coding.</p></li><li><p style="min-height:1.5em">A background in health-tech, clinical informatics or another regulated domain such as defence.</p></li><li><p style="min-height:1.5em">Experience with video data at scale (frame sampling, temporal annotation, multimodal datasets).</p></li><li><p style="min-height:1.5em">Familiarity with FHIR or HL7 interoperability standards.</p></li><li><p style="min-height:1.5em">Experience working with LLMs and VLMs, including edge or on-device deployment.</p></li><li><p style="min-height:1.5em">Early-stage startup experience, especially as a founding or early engineer.</p></li></ul><h3><strong>Probably not the right fit if</strong></h3><ul style="min-height:1.5em"><li><p style="min-height:1.5em">You need detailed specs and a large team around you to be effective.</p></li><li><p style="min-height:1.5em">You prefer pure research over building tools people use every day.</p></li></ul><p style="min-height:1.5em"></p><p style="min-height:1.5em">This is a high urgency opening, and we are flexible to consider applicants either on a more flexible consultancy agreement (rolling by mutual agreement, with a competitive day rate); or a long term permanent employment contract with shares as part of the package and scope to grow into a longer-term role as Tricorder builds its engineering team.</p><p>Find <a href="https://www.arbeitnow.co.uk">Jobs in United Kingdom</a> on Arbeitnow</a>