Data Scientist & LLM Engineer

The opportunity

The role

Our platform produces a rich stream of recordings, detections, tracks, events, and operational context. As a Data Scientist & LLM Engineer, you will turn that data into dependable features and build language- and vision-language workflows that help users understand what happened.

You will combine product thinking with careful experimentation. The goal is not a clever demo: it is an evaluated, observable system that behaves predictably with real customer data and makes its uncertainty visible.

Your impact

What you will work on

• Build vision-language and LLM workflows for summarisation, event understanding, search, and operational automation.
• Design evaluations, test sets, and feedback loops that measure quality, safety, latency, and cost.
• Explore event and media metadata to identify patterns that can become useful product capabilities.
• Develop retrieval and context strategies across structured data, model results, and selected media evidence.
• Productionise experiments as tested services or workflow stages with monitoring and clear failure behaviour.
• Work with product and engineering colleagues to scope problems, review output quality, and iterate from user feedback.

About you

You may thrive here if

• You are strong in Python and comfortable analysing data as well as building production software.
• You have practical experience with LLMs, vision-language models, retrieval, or adjacent applied-ML systems.
• You know how to evaluate probabilistic systems beyond a few hand-picked examples.
• You can work with structured and unstructured data and reason about provenance, access, and data quality.
• You communicate trade-offs clearly and prefer simple, testable approaches over unnecessary framework complexity.

You do not need to match every point. If the work sounds like a strong fit, tell us what you would bring and where you want to grow.

Useful additions

Helpful experience

• RAG, tool use, agent harnesses, or structured-output workflows
• Multimodal models that combine text, images, or video
• MongoDB aggregation, vector search, or large event datasets
• Evaluation tooling, observability, prompt versioning, or model gateways
• Media pipelines, computer vision, or time-series analytics