Agentic & Generative Edge AI Optimization Engineer
(m/f/d)
Freelance/Contracting project Munich Start date: asap Reference number: 854401/1
Diesen Job teilen oder drucken
Responsibilities
1. Investigate, develop and apply advanced quantization (8-bit, 4-bit, mixed precision), pruning, and distillation techniques for deriving optimized models for NXP NPU targets
2. Accelerate inference performance
3. Investigate methodologies for enhancing the performance of small language models towards enabling tiny agents at the edge, while ensuring these follow safety principles
4. Deploy optimized models using Ollama,, ONNX Runtime, and TFLite for efficient NPU inference
5. Design benchmarking pipelines for assessing the performance of Generative and Agentic AI systems on-device
6. Develop demonstrators and proof-of-concepts
7. Move key technologies from research into product solutions
Profile
8. Solid experience in software/AI engineering with deep exposure to LLMs, VLMs, and systems performance
9. Experience with LLM quantization techniques (, SmoothQuant, SpinQuant, QuaRoT), pruning (Wanda, SparseGPT, etc.) and other system optimizations like speculative decoding
10. Track-record experience in working with AI frameworks (PyTorch, TensorFlow, etc.), required
11. Experience with Agentic AI technologies and familiarity with existing frameworks (, LangChain, Google ADK, SmolAgents, etc.)
12. Understanding of AI toolchains, deployment, portability and inference engines (CUDA, TensorRT, TFLite, ONNX, Ollama, etc.) preferred
13. Affinity and experience with embedded systems, and NPU accelerators required
14. Experience with embedded software architecture, build systems, version control systems required
15. Broad experience with Operating systems GNU/Linux, embedded systems, development boards, and processors, and SW competencies required
16. Familiarity with setting up and maintaining related ML-Ops development environments (MLFlow, ClearML, etc.) required
17. Solid programming experience of C, C++, Python and Bash programming languages on Linux systems required
Benefits
18. You will work in an international environment
19. A very renowned company
20. Interesting tasks in a multinational environment