Research Manager | Production Inference
Core
Lead the Production Inference team responsible for serving DeepL's language AI models reliably and efficiently at scale.
Role type
Senior IC research manager (production inference systems)
Builds
GPU-resident inference runtimes, deployment infrastructure, and developer platforms for model serving
Domain
AI/ML, Large Language Models, Production Systems
Deliverable
production ML models
Required skills
Team leadership for researchers/ML engineers, production ML systems architecture, inference optimization, model serving at scale, infrastructure strategy, technical roadmap planning
Preferred skills
LLM inference experience, speculative decoding, quantisation, research publication experience
Technologies
GPU inference runtimes, load balancing, autoscaling, runtime selection
Responsibilities
Lead and develop a high-performing team of research scientists and ML engineers; Own the R&D roadmap for production inference systems; Act as primary technical interface between inference team and adjacent functions; Drive reliability, efficiency, and cost performance of the model serving stack; Identify, assess, and recruit research and engineering talent
Seniority
Senior, hands-on IC
