HPC ML Engineer — serving 5+ production LLMs on bare-metal Slurm (8× B200). Fine-tuning 31B agents with GRPO. Building AI infrastructure.
- Munich, Germany
Pinned Loading
-
hpc-llm-serving
hpc-llm-serving PublicProduction-grade multi-model LLM inference + LoRA fine-tuning on bare-metal Slurm clusters (8× B200). SGLang, vLLM, EAGLE, MTP speculative decoding.
Python
-
llm-gateway
llm-gateway PublicOpenAI-compatible multi-provider LLM gateway with failover, profile-based routing, and free-tier model catalog
Python
-
second-brain
second-brain PublicAI-powered second brain — project registry, Claude agents, and automation tools for analytics & AI strategy work
Python
-
voicetype
voicetype PublicLightweight Electron dictation overlay for Windows — Azure STT, push-to-talk via Win+Ctrl
JavaScript
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.