Senior LLM Inference Engineer — Remote-Friendly AI Platform

Doctolib; Paris; Hybrid; EUR 110,000 - 160,000; Full time

Benefits offered by this job

Health insurance

Lunch vouchers

Relocation support

Transport subsidy

DoctoGrowth program

Job summary

Doctolib Paris is seeking a Senior Inference Engineer to join the ML Platform (TIGER) team. You will own the self-hosted LLM serving platform, deploying and tuning open-weight models across our GPU fleet, and ensuring safety, cost efficiency, and scalability for Europe-wide healthcare AI features.

You will work with Ray Serve, Anyscale, Kubernetes, and Datadog, building robust foundations for AI products used by care teams and patients. Fluent English required.

Qualifications

• 5+ years of software or computer engineering experience, with production LLM serving experience.
• Proficient in Python and Terraform; strong understanding of transformer inference mechanics.
• Experience running GPU workloads on Kubernetes or Ray/Anyscale; performance benchmarking.
• Comfortable with production reliability, observability, on-call.
• Fluent in English.

Responsibilities

• Build the shared LLM serving foundations with MLOps engineers on GPU fleet.
• Own the model registry and promotion path; versioning and production readiness.
• Optimize inference performance and efficiency; reduce latency and cost per token.
• Own production reliability and disaster recovery; define SLOs and run load tests.
• Make serving performance and costs measurable with Datadog dashboards.
• Keep the inference stack secure, compliant, and evolving.

Skills

Python

Terraform

MLOps

Kubernetes

Ray Serve

LLM Serving

GPU infra

Observability

English

Tools

vLLM

TensorRT-LLM

Triton Inference Server

Ray Serve

Anyscale

Kubernetes

MLflow

Datadog

Job description

Doctolib Paris is seeking a Senior Inference Engineer to join the ML Platform (TIGER) team. You will own the self-hosted LLM serving platform, deploying and tuning open-weight models across our GPU fleet, and ensuring safety, cost efficiency, and scalability for Europe-wide healthcare AI features.

You will work with Ray Serve, Anyscale, Kubernetes, and Datadog, building robust foundations for AI products used by care teams and patients. Fluent English required.