- Apply prompt engineering strategies
- Build AI agents and orchestration pipelines
- Design and develop LLM agent workflows for embedded and edge platforms
- Design microservices architectures for AI deployment
- Develop multimodal AI systems
- Implement retrieval-augmented generation pipelines
- Integrate AI agents into distributed systems
- Optimize edge AI inference
- Quantize and tune models for performance
- Utilize NPU and GPU resources
Perks/Benefits:
- Access to cutting-edge technologies
- Collaborative work environment
- In office work week
- Professional growth
- Training and development