Senior ML Engineer, LLM/VLM Inference Optimizer

Jobgether SRL; France; Sur place; EUR 90 000 - 150 000; Plein temps

Avantages offerts par ce poste

Competitive compensation

Career growth

Ownership over technical work

Collaborative environment

International teams

Résumé du poste

Jobgether SRL, partnering with a France-based team, seeks a Senior Machine Learning Engineer focused on LLM and VLM inference optimization. You will drive latency, throughput, and memory improvements across model families, engines, and deployment backends, coordinating with kernel, platform, and product teams.

Role involves benchmarking, safe rollouts, and collaboration with international AI teams, delivering measurable performance gains in production systems.

Qualifications

• Strong Python and PyTorch software engineering skills.
• Hands-on experience deploying/optimizing high-throughput transformer inference systems.
• Experience with at least one modern inference stack (vLLM, TensorRT-LLM, Triton, etc.).
• Ability to reason quantitatively about latency, throughput, cost, and resource use.

Responsabilités

• Own optimization initiatives for model families and endpoints.
• Evaluate inference engines and serving configurations.
• Diagnose performance regressions during production rollouts.
• Deploy, benchmark, and extend inference engines (vLLM, Triton, etc.).
• Develop reproducible benchmark harnesses (TTFT, tokens/sec per GPU).
• Collaborate with kernel, platform, and product teams.
• Document design, performance reports, and rollout plans.

Connaissances

Python

PyTorch

LLM inference

Performance optimization

System benchmarking

CUDA/Triton

Communication

Open source

Outils

vLLM

TensorRT-LLM

Triton Inference Server

NVIDIA Dynamo

Ray Serve

KServe

SGLang

TorchServe

Description du poste

Jobgether SRL, partnering with a France-based team, seeks a Senior Machine Learning Engineer focused on LLM and VLM inference optimization. You will drive latency, throughput, and memory improvements across model families, engines, and deployment backends, coordinating with kernel, platform, and product teams.

Role involves benchmarking, safe rollouts, and collaboration with international AI teams, delivering measurable performance gains in production systems.