[{"data":1,"prerenderedAt":17},["ShallowReactive",2],{"$f9vTbcDkUWVf88c8L9dgBWmfUkEPAdkOOQtC2ugGlm3c":3},{"_id":4,"title":5,"slug":6,"tagline":7,"salary":8,"location":9,"contract":10,"departmentName":11,"image":12,"live":13,"departmentIcon":14,"level":15,"description":16},"698eff2142e4b97b3bbd0bcb","Data Scientist \u002F ML Engineer","data-scientist-ml-engineer","We are looking for an exceptional data scientist to join our technical team and help us turn vessel data into insight that matters, for our current customers and the new ones we're about to bring on board.","£60k +","London","Full time","Data Science","https:\u002F\u002Fimages.unsplash.com\u002Fphoto-1568992687947-868a62a9f521?q=80&w=3132&auto=format&fit=crop&ixlib=rb-4.0.3&ixid=M3wxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8fA%3D%3D",true,"material-symbols:analytics-sharp","Mid to Senior","\u003Cp class=\"ql-align-center\">\u003Cstrong>Data Scientist \u002F ML Engineer @ Ceto\u003C\u002Fstrong> \u003C\u002Fp> \u003Cp> \u003C\u002Fp> \u003Ch2>About Us\u003C\u002Fh2> \u003Cp> We're a rapidly growing maritime-focussed Insurtech startup passionate about technology and innovation. Last year we raised a $4.8M seed round from leading venture investors in maritime, supply chain and insurance. We've gained strong early traction including partnerships with major ship owners and are building serious momentum. We believe technology can and does make the world a better place, and we believe we can make that happen. We value challenging each other, truth seeking and creative problem solving. We celebrate the wins and always have fun. \u003C\u002Fp> \u003Cp> \u003C\u002Fp> \u003Ch2>What we're doing\u003C\u002Fh2> \u003Cp> We're reshaping maritime. It's an industry that's incredibly important and serves as the backbone of global trade, moving $14 trillion of cargo each year. Despite its significance, the industry remains one of the final frontiers of digitalisation. \u003C\u002Fp> \u003Cp> \u003C\u002Fp> \u003Cp> Ceto captures and analyses high frequency data from commercial ships to enrich insurance risk selection, reduce machinery breakdowns and improve fuel efficiency. The insights we derive are served to our customers in a beautiful dashboard, saving thousands of tonnes of CO2 emissions, preventing costly breakdowns and reducing operational risk. \u003C\u002Fp> \u003Cp> \u003C\u002Fp> \u003Ch2>The role\u003C\u002Fh2> \u003Cp> You'll build on our existing products and create new features for current and future customers, working across the full data science pipeline from data cleaning through to feature engineering, model training and deployment. You'll also be expected to offer broader engineering support, spotting and shipping improvements across our analytics stack wherever they're needed. \u003C\u002Fp> \u003Cp> \u003C\u002Fp> \u003Cp>Your responsibilities will include:\u003C\u002Fp> \u003Cul class=\"list-disc ml-4\"> \u003Cli>Exploring new ideas in predictive maintenance and condition monitoring, and turning them into reliable, production-ready features\u003C\u002Fli> \u003Cli>Building and maintaining data science pipelines end to end: cleaning, feature engineering, model training and inference, and output storage\u003C\u002Fli> \u003Cli>Investigating and resolving the nuances that come with new vessel types, sensors and tags as our customer base grows\u003C\u002Fli> \u003Cli>Working with time-series data and models, and applying both supervised and unsupervised techniques where they add genuine value\u003C\u002Fli> \u003Cli>Maintaining high standards of engineering practice: version control, testing, CI\u002FCD and experiment tracking\u003C\u002Fli> \u003Cli>Working closely with the rest of the technical team to prioritise what's worth investigating and what isn't\u003C\u002Fli> \u003Cli>Using AI tools such as Claude Code to work faster and more effectively\u003C\u002Fli> \u003C\u002Ful> \u003Cp> \u003C\u002Fp> \u003Ch2>You'll be perfect for this role if:\u003C\u002Fh2> \u003Cul class=\"list-disc ml-4\"> \u003Cli>You have a physics or physics-based degree, and a genuine interest in the physical systems behind the data, not just the data itself\u003C\u002Fli> \u003Cli>You've delivered real ML projects into production, not just in notebooks, with exposure to CI\u002FCD and DevOps practices\u003C\u002Fli> \u003Cli>You have solid experience with supervised ML models and can explain clearly why you'd choose one approach over another\u003C\u002Fli> \u003Cli>You've worked at a startup, or started your own, and are comfortable with the pace and ambiguity that comes with it\u003C\u002Fli> \u003Cli>You've built production data science pipelines before, from raw data through to a deployed, monitored output\u003C\u002Fli> \u003Cli>You have an innate ability to match models to physical problems, and know when a model is telling you something real versus something spurious\u003C\u002Fli> \u003Cli>You have brilliant problem-framing intuition and a strong desire to build something new\u003C\u002Fli> \u003Cli>You're a team player who is confident enough to challenge bad ideas and put forward your own, but self-aware enough to know when to do so\u003C\u002Fli> \u003Cli>You're sceptical by nature. Models can be wrong, intuition can be disproven, and correlations in data often have mundane explanations. You want to understand why, not just what\u003C\u002Fli> \u003Cli>You have a sense of the big picture and can judge which problems are worth your time and which aren't\u003C\u002Fli> \u003C\u002Ful> \u003Cp> \u003C\u002Fp> \u003Cp>It's also a bonus if you have:\u003C\u002Fp> \u003Cul class=\"list-disc ml-4\"> \u003Cli>Experience in predictive maintenance or predictive analytics\u003C\u002Fli> \u003Cli>Experience with cloud platforms, ideally Azure, or otherwise AWS or GCP\u003C\u002Fli> \u003Cli>Experience with MongoDB or other NoSQL databases\u003C\u002Fli> \u003Cli>Experience with unsupervised methods such as clustering or hidden Markov models\u003C\u002Fli> \u003Cli>Experience with ML lifecycle tooling such as MLflow\u003C\u002Fli> \u003Cli>Experience with anomaly detection\u003C\u002Fli> \u003Cli>A background around boats, cars, bikes or planes\u003C\u002Fli> \u003C\u002Ful> \u003Cp> We're less interested in ticking off niche experience like maritime or MongoDB specifically, and far more interested in someone who has worked across different technical stacks and can pick up new ones quickly. A strong generalist who's genuinely curious about the wider engineering problem, not just the modelling, will do better here than a narrow specialist. \u003C\u002Fp> \u003Cp> \u003C\u002Fp> \u003Ch2>What's on offer\u003C\u002Fh2> \u003Cul class=\"list-disc ml-4\"> \u003Cli>Competitive salary based on experience\u003C\u002Fli> \u003Cli>Equity options\u003C\u002Fli> \u003Cli>25 days holiday plus public holidays\u003C\u002Fli> \u003Cli>Birthdays off\u003C\u002Fli> \u003Cli>Bupa medical insurance\u003C\u002Fli> \u003Cli>Medicash\u003C\u002Fli> \u003Cli>Cycle to work scheme\u003C\u002Fli> \u003Cli>Hybrid working from either our London or Newcastle office\u003C\u002Fli> \u003Cli>All the kit you need to be productive\u003C\u002Fli> \u003Cli>£500 work from anywhere flight allowance\u003C\u002Fli> \u003Cli>£100 budget and time allocation for conferences and professional development\u003C\u002Fli> \u003Cli>The opportunity to shape the future of maritime and insurance technology\u003C\u002Fli> \u003C\u002Ful> \u003Cp> \u003C\u002Fp> \u003Cp>Join us if you want to be part of a team making a real dent in two huge industries.\u003C\u002Fp>",1783526570055]