Director, Production ML Inference & Systems

DeepL; Amsterdam; Hybrid; EUR 120,000 - 180,000; Full time

Benefits offered by this job

Hybrid work

Virtual Shares

30 days annual leave

Hack Fridays

Regular team events

Competitive benefits

Diverse and international team

Job summary

DeepL is seeking an Engineering Manager for the Production Inference team. You will lead researchers and ML engineers focused on reliable, scalable model serving at scale, sitting at the intersection of research ambition and production discipline.

You will drive the roadmap, coordinate with cross-functional partners, and ensure architectural choices support latency, reliability, and cost goals while growing talent and fostering a culture of rigor and innovation.

Qualifications

• Proven experience leading researchers or ML engineers and delivering impact.
• Strength in production ML systems, inference optimization, or model serving at scale.
• Excellent communication to translate technical direction for diverse stakeholders.
• Ability to operate across the full model lifecycle from training handoff to deployment.
• Comfort working in a fast-moving AI org with ambiguity and changing requirements.

Responsibilities

• Lead and develop a high-performing team of researchers and ML engineers.
• Own the team's research and development roadmap for production inference systems.
• Act as the primary technical interface between the team and adjacent functions.
• Drive reliability, efficiency, and cost performance of the model serving stack.
• Define strategic direction and push for results with autonomy.
• Identify, assess, and recruit research and engineering talent.

Skills

Team leadership

ML systems

Production inference

Architectural direction

Communication skills

Education

Computer Science

Mathematics/Physics

Tools

PyTorch

TensorFlow

Kubernetes

GPU clusters

Job description

DeepL is seeking an Engineering Manager for the Production Inference team. You will lead researchers and ML engineers focused on reliable, scalable model serving at scale, sitting at the intersection of research ambition and production discipline.

You will drive the roadmap, coordinate with cross-functional partners, and ensure architectural choices support latency, reliability, and cost goals while growing talent and fostering a culture of rigor and innovation.