Senior Machine Learning Engineer (W/M/X)

Description

The company is data-driven throughout, from game design to marketing decisions, and relies on data and algorithms across the business.

The team sits in the Player Domain of the company's Data Office and works on player safety and security.

The team builds and deploys machine learning systems that protect players, such as detecting sanction circumvention with Graph Neural Networks (GNNs) and spotting toxic chat in real time with transformer models.

The work spans NLP, anomaly detection, graph learning, and large language models.

The company is a global games developer with teams around the world.

Responsibilities

• Build scalable machine learning systems that protect players' trust and safety.
• Take projects beyond prototypes by alternating research and engineering cycles, with the aim of shipping production-grade products that reach many players.
• Work on difficult problems across NLP, anomaly detection, graph learning, and LLMs.
• Design, train, and deploy ML models for player safety and security, including NLP, anomaly detection, and graph-based learning.
• Apply the latest research in deep learning, NLP, and graph learning to production needs, implementing methods from scratch when required.
• Own your projects end to end: work with stakeholders, set success metrics, monitor live systems, and keep improving them.
• Write, optimise, and ship high-quality code that performs at scale, using modern MLOps practices such as CI/CD, model versioning, and observability.
• Work with data and software engineers to move models and prediction pipelines into production on internal or public cloud infrastructure.

Requirements

• You have proven experience moving machine learning models into production and monitoring them.
• You write strong Python: clean, tested, documented code with CI/CD.
• You have hands-on experience with NLP or LLMs, such as fine-tuning transformers, prompt engineering, RAG, or LLM-based pipelines.
• You have worked with anomaly detection or fraud and trust and safety systems in production.
• You are comfortable with MLOps, model serving, and drift monitoring.
• You communicate well and can present, collaborate across teams, and report clearly in English, which is mandatory.
• You have experience with distributed data processing in Spark and with cloud data platforms.
• Experience with graph-based ML (GNNs) is a strong plus.
• Familiarity with Databricks (DAB, Delta Live Tables) or Azure-specific services is a plus.
• Ideal candidate: experience with token classification (NER, sequence labelling) and/or hands-on GNN training (node classification, link prediction, graph construction pipelines).

Conditions

The office is in Saint Mandé, a short walk from Saint Mandé station on metro line 1.

The building has a gym.

The company offers equal job opportunities regardless of gender, ethnicity, religion, sexual orientation, social status, disability, or age.

Benefits

• Profit sharing and a yearly company savings plan.
• 25 paid vacation days plus 12 additional paid days off.
• The company pays 50% of your transport pass.
• Lunch vouchers worth 9€ per day.
• Healthcare coverage for you and your family.
• Maternity leave of 20 weeks and paternity or co-parental leave of 7 weeks.
• Additional perks from the company.