Insight Enterprises, Inc.
Principal Engineer- Local AI/Hardware AI
- Hybrid
- Full-time
$8.2 USD
... Working familiarity with running local models on NVIDIA GB10 (Grace Blackwell / CUDA) and Apple Silicon (unified memory / MLX) hardware, alongside developer tools (e.g., Ollama, vLLM, LM Studio). - Understanding of core LLM mechanics, prompt design, API/Console usage, tool integration, and foundational agent patterns. ...
Gurgaon, भारत