Engineering Manager (Production Inference)

Location: London, Amsterdam, or Munich; hybrid work with office attendance twice a week and flexible hours.

Company

DeepL is a global AI product and research company building secure language AI solutions for translation, writing improvement, and real-time voice translation.

What you will do

• Lead and develop a team of research scientists and ML engineers, including development planning, feedback, technical rigour, and delivery standards.
• Own the research and development roadmap for production inference systems, balancing reliability commitments with longer-term research into inference efficiency and architecture.
• Serve as the technical interface with foundational models research, voice research, applied research, infrastructure, and product teams.
• Drive reliability, efficiency, and cost performance across the model-serving stack, including load balancing, autoscaling, runtime selection, and hardware utilisation.
• Define team direction autonomously, resolve ambiguous or evolving requirements, and recruit research and engineering talent.

Requirements

• Proven experience leading researchers or ML engineers, developing talent, maintaining delivery rigour, and balancing research quality with production reliability.
• Strong background in Computer Science, Mathematics, Physics, or a comparable quantitative discipline, or an equivalent ML/systems background with research depth.
• Strong foundation in production ML systems, inference optimisation, or model serving at scale.
• Experience across the model lifecycle, from training handoff through production deployment, monitoring, and efficiency improvement.
• Understanding of infrastructure and compute constraints without needing to own them directly.
• Excellent communication skills, with the ability to translate complex technical direction into clear goals for technical and non-technical stakeholders.
• Solution-oriented and decisive approach, with the ability to define direction and drive outcomes autonomously.

Nice to have

• Direct experience with LLM inference, speculative decoding, quantisation, or serving infrastructure.

Culture & Benefits

• Internationally distributed team with more than 90 nationalities and employees across the UK, Germany, the Netherlands, Poland, the US, and Japan.
• Open communication, regular direct feedback, empathy, and a growth mindset.
• Virtual Shares for every employee.
• Regular in-person team events and monthly full-day Hack Fridays for cross-team projects.
• 30 days of annual leave excluding public holidays, mental health resources, and location-tailored benefits.