AI software Engineer - Project Tricorder
Founders Factory6 hours ago
London, United KingdomSenior
Responsibilities
- Design labelling schemas and guidelines, set up annotation tooling, coordinate clinical labelling, and perform quality checks including inter-annotator agreement.
- Build reproducible pipelines to ingest, clean, de-identify, and transform video, sensor, and text data.
- Organize, version, and catalogue video datasets with searchable and traceable clips, annotations, and metadata.
- Prepare balanced, documented training, validation, and test datasets with lineage from raw data to model input.
- Build an automated evaluation harness for vision-language and NLP models, including clinically meaningful metrics, regression tracking, and build-versus-buy analysis.
- Design the clinical knowledge-base schema and data store for clinical concepts and relationships.
- Ingest and map TC3, SNOMED CT, ICD-10, and related NHS standards, including cross-mappings.
- Extract and link entities and relationships from clinical text to coded concepts.
- Parse and structure clinical documents including PDFs, notes, and forms.
- Work with clinicians to align the knowledge base with clinical reasoning and pre-hospital workflows.
- Deliver a working evaluation harness, versioned core dataset, and initial product-linked knowledge base within the first three months.
Requirements
- Strong Python and data engineering skills with a track record of shipping production data or ML pipelines.
- Hands-on experience building ML evaluation frameworks, benchmarks, or test harnesses, ideally for vision, video, or language models.
- Experience running data labelling and training-data preparation, including annotation tooling and quality control.
- Working knowledge of databases and data modelling.
- Practical NLP experience in entity extraction, entity linking, or document parsing.
- Ability to handle sensitive data under data protection and clinical safety constraints.
- Pragmatic, fast-paced approach to ambiguity, build-versus-buy decisions, and shipping quickly.
- Experience with SNOMED CT, ICD-10, dm+d, or other NHS clinical terminologies is preferred.
- Background in health technology, clinical informatics, defence, or another regulated domain is preferred.
- Experience with video data at scale, including frame sampling, temporal annotation, or multimodal datasets, is preferred.
- Familiarity with FHIR or HL7 interoperability standards is preferred.
- Experience with LLMs and VLMs, including edge or on-device deployment, is preferred.
- Early-stage startup experience, especially as a founding or early engineer, is preferred.
Benefits
- Flexible consultancy agreement available on a rolling basis by mutual agreement with a competitive day rate.
- Long-term permanent employment contract available with shares as part of the package.
- Scope to grow into a longer-term engineering role as Tricorder builds its team.
Tech Stack
Categories
Data Engineering
About Founders Factory
Founders Factory is a London-based venture studio, accelerator, and fund that co-founds and backs early-stage startups with capital and hands-on operational support. It partners with large enterprises (e.g., Aviva, Rio Tinto, HSBC) to provide pilots, distribution, and domain expertise, and earns returns through equity in portfolio companies. Founded in 2015, it has backed more than 450 startups across fintech, health, and industrials/deep tech.