Senior Machine Learning Engineer

We are reimagining data-driven advertising by turning publisher first-party data into predictive, privacy-safe signals that allow advertisers to purchase only the impressions most likely to deliver results.

Our optimisation engine improves outcomes such as click-through rate, attention, video completion, and sales — enabling advertisers to achieve stronger performance while helping publishers monetise their audiences more effectively.

We are a pre-seed startup with a small, core team of four, backed by Tier-1 investors. Joining us now means becoming part of the founding team shaping the core technology and product.

The Role

We’re looking for a Senior Machine Learning Engineer to lead the design, training, and deployment of our optimisation models at scale. You’ll build ML systems that predict ad outcomes, integrate them into live ad-serving environments (e.g. Google Ad Manager, Prebid, SSPs), and ensure they operate reliably in real-time, high-volume settings.

This is a hands-on, high-impact role where every model you ship will directly change which Impressions are bought and sold.

Key Responsibilities

Model development: Design, train, and optimise ML models that predict outcomes such as CTR, attention, video completion, and advertiser sales.
Feature engineering: Build feature sets from publisher first-party signals (contextual, behavioural, declared, device-level) and advertiser/category data.
Deployment at scale: Deliver real-time inference systems capable of scoring millions of impressions per day.
MLOps & infrastructure: Establish reproducible pipelines, CI/CD for ML, and monitoring systems to ensure performance and reliability in production.
Experimentation: Run tests, measure lift against benchmarks, and iterate rapidly.
Innovation: Apply the latest advances in applied ML to real-world optimisation challenges in digital advertising.

Must-have skills:

5+ years of experience building and deploying ML models in production.
Strong expertise in Python and modern ML frameworks (TensorFlow, PyTorch, Scikit-learn).
Experience with real-time or large-scale ML systems (ads, recommender systems, fraud detection, or similar).
Hands-on experience with cloud environments (GCP preferred) and distributed systems (BigQuery, Spark, Airflow, Kubernetes, Docker).
Solid grounding in MLOps (CI/CD for ML, monitoring, retraining pipelines).
Ability to design experiments, analyse results, and iterate quickly.
Strong problem-solving mindset with bias for action.

Nice-to-haves:

Experience in adtech, programmatic bidding, or recommender systems.
Knowledge of vector databases, embeddings, or category-level modelling.
Familiarity with Prebid, SSP/DSP integrations, or GAM workflows.
Contributions to open-source ML or published applied research.
Early-stage startup experience (0→1 product builds).

Why Join Us?