AI role · Open offer

Lead MLOps Engineer — GPU clusters & vLLM

Focus: Enterprise AI

Paris · 1000-2000 employees · Scale-up · GenAI: Partial

This listing is optimized for AI-native talent: clear skills and tools so candidates know if they fit before they apply—and so you spend less time screening mismatches.

4 skills1 tool

Apply now Find matching talent

Share this role

At a glance

How you'll work, where, and key listing dates.

Employment: Freelance, Full-time
Workplace: Hybrid
Location: Amsterdam, Netherlands · Hybrid
Compensation: €95k–€125k or competitive day-rate path
Experience level: Lead
Team: ML platform
Benefits & perks

About this role

What the team is looking for and how this position fits.

Our Amsterdam-based ML platform team owns GPU pools, model registry, and predictable rollouts for dozens of internal teams. You will set technical direction as we expand multi-cloud options.

Hybrid role with flexible EU remote weeks; on-call rotation is shared and compensated.

What you will do

Own vLLM/ONNX gateway roadmaps, scaling tests, and failover drills.
Define FinOps guardrails: quotas, chargeback views, and alerting for runaway jobs.
Partner with security for image hardening, artefact signing, and egress policies.
Mentor engineers on distributed systems debugging and post-incident learnings.
Evaluate vendor accelerators (Run:ai, Determined, SageMaker) with pragmatic scorecards.

What we look for

7+ years infra/platform experience with hands-on Kubernetes and cloud networking.
Track record improving GPU utilisation and inference cost metrics measurably.
Comfort translating DS needs into SLO-backed platform features.

Nice to have

NVIDIA ecosystem fluency (CUDA, Triton, NCCL tuning).
OpenTelemetry champion.

Skills we're hiring for

Core capabilities—LLMs, automation, analytics, product, or domain expertise.

PythonKubernetesAWSDocker

Tools & stack

Platforms and products mentioned for this role (APIs, IDEs, vector DBs, CRMs, design tools, etc.).

PostgreSQL

You're a strong fit if…

You've shipped real work with AI—not only experimented in isolation.
Several listed skills or tools show up in your recent projects.
You can explain trade-offs (quality, cost, latency, safety) in plain language.

Apply

Candidate accounts only: add your headline and bio on , and optionally a CV link or PDF so recruiters see your full résumé. Then write a short pitch below—applications use your login email.

What the employer asked for

Describe one incident where you rolled back a bad model version safely.

Register, add a headline and bio, then you can attach a CV link or PDF on My account before you apply. That keeps applications tied to your profile and makes it easier for employers to review your background.

Suggested

AI talent you may also like

Profiles ranked by overlap with this role's skills and tools—handy if you're hiring for a team or comparing backup candidates.

Marcus Thorne

ML Platform Lead

Open to contract-to-hire · $180k–220k TC · Remote · US East

Profile active · Apr 5

4 skills · 1 project · 1 role · 3 use cases

Built

Model flight deck
Internal UI for promote/rollback, canary traffic, and SLO dashboards per model version.
Demo Link

Top skills

PythonPyTorch

Similar open roles

Other listings that share skills or tools with this one—useful if you want comparable stacks or backup options.

Lead MLOps Engineer — GPU clusters & vLLM

AI talent you may also like

Marcus Thorne

Similar open roles

Omar El-Sayed

Camila Rojas

James Okoro

Viktor Novak

Senior ML Platform Engineer

Lead MLOps Engineer — GPU serving & FinOps

Freelance MLOps Engineer — Kubernetes & model serving

Senior Backend Engineer — Geo data pipelines

Senior AI Site Reliability Engineer — inference SLOs