Für unseren Kunden aus München suchen wir nach einem ML Engineer (m/w/d).
The problem you are solving
Our customer and product embedding models are in production and generating business impact already in personalized product retrieval in sorting. The infrastructure and architecture holding us up — training pipelines, feature loading, model training time— needs to be rebuilt or adjusted for scale and speed. We also need to lay the groundwork for real-time inference.
Specifically, you will work on one or more of:
- Reducing training data load times, ensuring train/serve consistency, enabling feature reuse across model versions of a two-tower neural Network
- Horizontal scaling of TensorFlow training, including GPU utilisation optimisation
- Inference & Training pipeline: reliable, low-latency serving of embeddings and rankings at scale
- Real-time personalisation groundwork: architecture for updating customer representations at inference time without full model retraining — requires deep understanding of how embeddings work and how they can be modified at serving time
- Suggest and implement architectural changes in the model to improve quality
You are the right fit if you have:
- Proven experience building ML infrastructure in production — not prototype pipelines, but systems that serve real traffic reliably
- Deep TensorFlow and Pytorch production experience (not just training scripts)
- Hands-on experience with training and operating large neural networks at scale
- Specific knowledge of embedding-based systems and low-latency inference is strongly preferred for the real-time workstream
Projectdetails:
Location: Full remote , full time
Contract period: asap until 31.12.2026
Grafton: Dein vertraulicher Partner in der Fach- und Führungskräftevermittlung. Bei uns hat Chancengleichheit höchste Priorität.
Informationen zum Umgang mit deinen Daten findest du in unseren Datenschutzerklärung.
