Senior LLM Inference Optimization Engineer

Jobgether SRL; Lavamünd; Vor Ort; EUR 148.000 - 201.000; Vollzeit

Benefits dieser Stelle

Competitive pay

Career growth

Flexible work

Collaborative environment

Impactful projects

Advanced AI tech

International team

Zusammenfassung

Jobgether SRL is seeking a Senior Machine Learning Engineer focused on LLM and VLM inference optimization, based in Switzerland. You will drive latency, throughput, and cost improvements across model artifacts, inference engines, and deployment architectures while collaborating with cross-functional teams to deliver measurable performance gains.

You will evaluate serving configurations, diagnose regressions, and implement advanced techniques such as quantization, distillation, and speculative

Qualifikationen

• Strong software engineering skills in Python and PyTorch.
• Hands-on experience deploying, operating, or optimizing LLM/VLM inference systems.
• Experience with at least one modern inference stack (vLLM, SGLang, TensorRT-LLM, Triton, NVIDIA Dynamo, Ray Serve, KServe).
• Strong understanding of transformer inference bottlenecks (KV cache, attention, memory bandwidth, batching).

Aufgaben

• Own optimization initiatives for model families and inference backends.
• Evaluate inference engines and recommend practical serving configurations.
• Diagnose and resolve model quality, performance, and reliability regressions during production rollouts.
• Optimize endpoints for latency, throughput, memory efficiency, GPU utilization, and cost per token.
• Deploy, benchmark, and extend inference engines (e.g., vLLM, TensorRT-LLM, Triton).
• Build model-compression workflows (quantization, distillation, low-bit serving).
• Implement advanced inference techniques (speculative decoding, KV-cache optimizations, continuous batching).
• Develop reproducible benchmark harnesses (TTFT, tokens/sec/GPU, p95/p99 latency).
• Collaborate with kernel/platform engineers to identify bottlenecks across stack.

Kenntnisse

Python

PyTorch

LLM Inference

Performance Tuning

Benchmarking

Distributed Systems

CUDA/Triton

Open Source

Tools

vLLM

SGLang

TensorRT-LLM

Triton Server

NVIDIA Dynamo

Ray Serve

KServe

CUDA

Jobbeschreibung

Jobgether SRL is seeking a Senior Machine Learning Engineer focused on LLM and VLM inference optimization, based in Switzerland. You will drive latency, throughput, and cost improvements across model artifacts, inference engines, and deployment architectures while collaborating with cross-functional teams to deliver measurable performance gains.

You will evaluate serving configurations, diagnose regressions, and implement advanced techniques such as quantization, distillation, and speculative