Senior Machine Learning Engineer, LLM Inference Optimization

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

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior Machine Learning Engineer, LLM Inference Optimization based in Switzerland.

As a Senior Machine Learning Engineer, you will drive the optimization of large language and vision-language model inference from model artifacts through production deployment. You will work across model internals, inference engines, serving architectures, and benchmarking to improve latency, throughput, memory efficiency, GPU utilization, reliability, and cost per token. This is a hands-on role focused on solving complex performance challenges and delivering measurable improvements to production systems. You will collaborate closely with kernel, platform, infrastructure, research, product, and customer-facing teams. Your work will involve evaluating serving configurations, diagnosing performance and quality regressions, and implementing advanced inference optimization techniques. You will also establish reproducible benchmarks and safe rollout practices for high-throughput AI workloads.

Accountabilities

• Own optimization initiatives for specific model families, customer endpoints, and inference serving backends.
• Evaluate inference engines and recommend practical serving configurations based on workload requirements.
• Diagnose and resolve model quality, performance, and reliability regressions during production rollouts.
• Optimize LLM and VLM endpoints for latency, throughput, memory efficiency, GPU utilization, model quality, and cost per token.
• Deploy, configure, benchmark, and extend modern inference engines such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, NVIDIA Dynamo, or equivalent technologies.
• Build and productionize model-compression workflows, including quantization, quantization-aware training, distillation, low-bit serving, and accuracy recovery.
• Implement or integrate advanced inference techniques such as speculative decoding, draft models, KV-cache optimization, prefix caching, chunked prefill, continuous batching, and disaggregated prefill/decode serving.
• Develop reproducible benchmark harnesses covering TTFT, TPOT, tokens per second per GPU, p95/p99 latency, GPU memory usage, reliability, and cost per token.
• Partner with GPU kernel and platform engineers to identify bottlenecks across model code, kernels, runtimes, schedulers, gateways, and cluster infrastructure.
• Investigate performance trade-offs quantitatively and use benchmark results to guide optimization decisions.
• Produce clear design documentation, performance reports, rollout plans, and technical explanations for internal and customer-facing stakeholders.
• Contribute to safe, measurable, and reliable production rollouts of inference improvements.

Requirements

• Strong software engineering skills in Python and PyTorch.
• Hands-on experience deploying, operating, or optimizing LLM, VLM, or high-throughput transformer inference systems.
• Practical experience with at least one modern inference stack, such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, NVIDIA Dynamo, Ray Serve, KServe, or an equivalent internal system.
• Strong understanding of transformer inference bottlenecks, including KV cache, attention mechanisms, memory bandwidth, batching, parallelism, and long-context serving.
• Ability to reason quantitatively about latency, throughput, model quality, resource utilization, and cost trade-offs.
• Experience diagnosing complex performance problems and translating findings into production improvements.
• Strong communication skills and the ability to collaborate effectively with research, kernel, infrastructure, product, and customer teams.
• Experience with quantization-aware training, post-training quantization, FP8, INT8, INT4, NVFP4, MXFP4, AWQ, GPTQ, SmoothQuant, or related optimization techniques is a plus.
• Familiarity with distillation, speculative decoding, EAGLE, Medusa, multi-token prediction, or other inference acceleration approaches is advantageous.
• Experience supporting agentic workloads involving tool calling, structured outputs, streaming APIs, high concurrency, or multi-step orchestration is a plus.
• Familiarity with CUDA or Triton is beneficial, even if the role is not primarily focused on kernel engineering.
• Contributions to open-source projects such as vLLM, SGLang, TensorRT-LLM, FlashInfer, LMCache, PyTorch, Triton, Ray, KServe, or related technologies are advantageous.
• Ability to work independently, take ownership, and operate effectively in a fast-moving technical environment.

Benefits

• Competitive compensation.
• Career growth and continuous learning opportunities.
• Flexibility and significant ownership over technical work.
• Collaborative and innovative working environment.
• Opportunity to work on impactful AI infrastructure and inference optimization projects.
• Exposure to advanced LLM and VLM serving technologies and large-scale AI workloads.
• International environment with experienced engineering and AI teams.