Domäne
Machine Learning & AI
Skill-Profil
Dieser Skill definiert Erwartungen über Rollen und Level.
Rollen
1
wo dieser Skill vorkommt
Stufen
5
strukturierter Entwicklungspfad
Pflichtanforderungen
0
die anderen 5 optional
Machine Learning & AI
LLM & Generative AI
22.2.2026
Wählen Sie Ihr aktuelles Level und vergleichen Sie die Erwartungen.
Die Tabelle zeigt, wie die Tiefe von Junior bis Principal wächst.
| Rolle | Pflicht | Beschreibung |
|---|---|---|
| LLM Engineer | Knows vLLM basics: what is PagedAttention, continuous batching, inference serving. Launches vLLM server for pre-trained model inference with basic configuration under mentor guidance. |
| Rolle | Pflicht | Beschreibung |
|---|---|---|
| LLM Engineer | Independently configures vLLM for production: tensor parallelism, quantization (AWQ/GPTQ), GPU memory management. Optimizes throughput by tuning batch size and scheduling parameters. |
| Rolle | Pflicht | Beschreibung |
|---|---|---|
| LLM Engineer | Designs production vLLM infrastructure: multi-model serving, speculative decoding, custom sampling strategies. Optimizes latency and throughput through advanced configuration and hardware-specific tuning. |
| Rolle | Pflicht | Beschreibung |
|---|---|---|
| LLM Engineer | Defines vLLM deployment standards for the LLM team. Establishes guidelines for configuration, monitoring, capacity planning. Coordinates upgrades and migration between vLLM versions. |
| Rolle | Pflicht | Beschreibung |
|---|---|---|
| LLM Engineer | Shapes enterprise vLLM inference strategy. Defines approaches to multi-cluster inference, hardware planning (A100/H100/H200), and cost optimization. Ensures SLA for critical inference workloads. |