4 days ago

Research Manager | Production Inference

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 22 hours agoStatus: Live

Job Summary

Lead DeepL’s Production Inference team responsible for the production model-serving stack that delivers low-latency, reliable, and cost-efficient AI inference at scale. Own people leadership and the technical direction for research scientists and ML engineers, set the roadmap for inference systems, and serve as the primary technical interface with adjacent research and infrastructure functions. Drive reliability, efficiency, and cost performance while recruiting and shaping the team.

Location: London, Munich

Workplace: Hybrid

Employment Type: Full time

Job Function: Manufacturing & Production Operations

Seniority: Manager level

Key Responsibilities

•Lead and develop a high-performing team of research scientists and ML engineers, building development plans and maintaining technical rigour and delivery.
•Own the research and development roadmap for production inference systems in collaboration with senior ICs and cross-functional stakeholders.
•Serve as the primary technical interface between Production Inference and adjacent functions (foundational models, voice, applied research, infrastructure, product).
•Drive reliability, efficiency, and cost performance of DeepL’s model serving stack, including infrastructure evolution decisions like load balancing and autoscaling.
•Recruit and assess research and engineering talent as the team grows while defining direction and operating with autonomy.

Pay and Benefits

Perks:Flexible HoursHybrid WorkAnnual LeaveHealth Insurance

Key Requirements

•PhD (preferable) in Computer Science, Mathematics, Physics, or a comparable quantitative discipline, or equivalent ML/systems research depth.
•Strong foundation in production ML systems, inference optimisation, or model serving at scale, including experience with LLM inference, speculative decoding, quantisation, or serving infrastructure.
•Proven experience leading a team of researchers or ML engineers, developing talent, and maintaining a balance between research quality and production reliability.
•Comfort operating across the full model lifecycle from training handoff to production deployment, monitoring, and efficiency improvement.
•Excellent communication skills to translate complex technical direction into clear goals for technical and non-technical stakeholders.

Skills:People leadershipTechnical reviewCommunicationSolution-orientationDecision-making

Tech Stack:LLM inferenceSpeculative decodingQuantisationLoad balancingAutoscalingRuntime selectionGPU-resident inference runtimesModel serving stackHardware utilisation

Company Brief

DeepL

DeepL builds Language AI products (DeepL Translator, DeepL Write, APIs and enterprise solutions) that provide high-accuracy translations and writing assistance to businesses and individuals, focusing on privacy, security and enterprise deployment.

Industry: AI & Machine Learning

Company Size: Enterprise (1,001+ employees)

Growth: Scaleup

Valuation: Unicorn (USD 1B+)

Funding: Series D

Headquarters: Cologne, Germany

Founded: 2017

Glassdoor: 3.5

Website LinkedIn Glassdoor

Loading job details...

Preparing the role view and application actions.

DeepL

4 days ago

Research Manager | Production Inference

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 22 hours agoStatus: Live

Job Summary

Location: London, Munich

Workplace: Hybrid

Employment Type: Full time

Job Function: Manufacturing & Production Operations

Seniority: Manager level

Key Responsibilities

•Lead and develop a high-performing team of research scientists and ML engineers, building development plans and maintaining technical rigour and delivery.
•Own the research and development roadmap for production inference systems in collaboration with senior ICs and cross-functional stakeholders.
•Serve as the primary technical interface between Production Inference and adjacent functions (foundational models, voice, applied research, infrastructure, product).
•Drive reliability, efficiency, and cost performance of DeepL’s model serving stack, including infrastructure evolution decisions like load balancing and autoscaling.
•Recruit and assess research and engineering talent as the team grows while defining direction and operating with autonomy.

Pay and Benefits

Perks:Flexible HoursHybrid WorkAnnual LeaveHealth Insurance

Key Requirements

•PhD (preferable) in Computer Science, Mathematics, Physics, or a comparable quantitative discipline, or equivalent ML/systems research depth.
•Strong foundation in production ML systems, inference optimisation, or model serving at scale, including experience with LLM inference, speculative decoding, quantisation, or serving infrastructure.
•Proven experience leading a team of researchers or ML engineers, developing talent, and maintaining a balance between research quality and production reliability.
•Comfort operating across the full model lifecycle from training handoff to production deployment, monitoring, and efficiency improvement.
•Excellent communication skills to translate complex technical direction into clear goals for technical and non-technical stakeholders.

Skills:People leadershipTechnical reviewCommunicationSolution-orientationDecision-making

Tech Stack:LLM inferenceSpeculative decodingQuantisationLoad balancingAutoscalingRuntime selectionGPU-resident inference runtimesModel serving stackHardware utilisation

Company Brief

DeepL

Industry: AI & Machine Learning

Company Size: Enterprise (1,001+ employees)

Growth: Scaleup

Valuation: Unicorn (USD 1B+)

Funding: Series D

Headquarters: Cologne, Germany

Founded: 2017

Glassdoor: 3.5

Website LinkedIn Glassdoor