Engineering Manager, Production Inference (Hybrid)

Deepl; Greater London; Hybrid; GBP 110,000 - 170,000; Full time

Benefits offered by this job

Hybrid work

Virtual Shares

Hack Fridays

30 days annual leave

Regular in-person team events

Competitive benefits

Job summary

DeepL in the United Kingdom is seeking an Engineering Manager for the Production Inference team to lead a group of researchers and ML engineers focused on scalable, reliable language AI model serving. You will shape technical direction and manage delivery.

This role blends research ambition with production discipline, requiring strong leadership, strategic roadmapping, and collaboration with product and infrastructure teams.

Qualifications

• Proven experience leading researchers or ML engineers with delivery rigour.
• Strong background in CS/Math/Physics or ML systems with research depth.
• Experience with production ML systems and model serving at scale.

Responsibilities

• Lead and develop a high-performing team of researchers and ML engineers.
• Own the team's research roadmap for production inference systems.
• Act as technical interface with adjacent functions ensuring clear goals.
• Drive reliability, efficiency and cost performance of the model serving stack.
• Identify and recruit research and engineering talent.
• Operate with autonomy, defining direction amidst ambiguity.

Skills

Team leadership

Production ML systems

LLM inference

Communication

Strategic planning

Education

Bachelor's degree in CS/Math/Physics

Tools

TensorFlow/PyTorch

Kubernetes

GPU inference runtimes

Job description

DeepL in the United Kingdom is seeking an Engineering Manager for the Production Inference team to lead a group of researchers and ML engineers focused on scalable, reliable language AI model serving. You will shape technical direction and manage delivery.

This role blends research ambition with production discipline, requiring strong leadership, strategic roadmapping, and collaboration with product and infrastructure teams.