Senior Machine Learning Engineer (f/m/d)
Indexed description
50 Billion Daily Bid Predictions
The adjoe Ads Data Science team owns the entire bidding algorithm that decides which ad you are most likely to enjoy from start to finish: conversion prediction, user quality estimation, and bid shading. Every bid adjoe placed in an ad auction is the output of ML models making 50 billion predictions daily, trained on data from our mobile SDKs that capture real user behavior at scale.
The team moves fast: new ideas tested offline, A/B tests launched in production within minutes. We rely on industry-proven state of the art technology, adapted to our needs and self-hosted where it matters: PyTorch and TensorFlow for modeling, Trino and Athena for querying a 350TB Iceberg data lake, Airflow and Ray for orchestrating our different training pipelines across multiple GPU clusters. Models are built on 600+ features and trained on 200 million data points, with the full ML lifecycle owned by the team from research and experimentation to deployment and real-time inference at sub-200ms latency.
Your Mission & Who We Are Looking For:
- 5+ years building production-grade recommendation systems. You've deployed large-scale systems in high-volume environments (adtech, e-commerce, or search), and have hands-on expertise in deep learning with TensorFlow, PyTorch, or JAX. At adjoe Ads, that means architecting high-throughput, low-latency systems that scale to 10 billion daily predictions.
- End-to-end model ownership. You own the full ML lifecycle from identifying relevant signals in large datasets and developing relevance models and bidding strategies, to rigorous monitoring, performance analysis, and iterative improvement in production.
- Engineer first, data scientist second. You write production-quality code, design for scalability, and collaborate closely with backend engineering teams to ensure seamless integration of reusable models and assets into the broader system.
- Experimentation is part of your workflow. You run rigorous A/B tests, validate hypotheses, and measure the impact of new features on key business metrics, not just offline evaluation.
- Plus: data engineering fluency. Understanding of data engineering principles and experience with distributed processing systems like Spark, Flink, or Kafka, and storage solutions like AWS Athena, S3, or MySQL is a strong plus.
- Go Big. Own projects with impact on 770M users and push adtech boundaries.
- Move Fast. Ship solutions multiple times a day, learn from results, and keep momentum.
- Be Direct. Solve problems openly and collaborate across teams.
- Thrive Together. Grow with a diverse, global team of people from over 40 different countries that learn from each other.
- Have Fun. Celebrate wins, enjoy daily victories, and bring your energy.
Create a free Caio profile to unlock more results and save your role and location preferences.
Unlock free search