We are seeking a versatile and experienced AI Engineer with expertise in NLP, LLMs, and CNNs
You will:
- Design and develop unified system for multiple AI models, including both cloud-based and local LLMs and CNNs.
- Collaborate with cross-functional teams to develop scalable, intelligent solutions for text and vision-based applications.
- Build infrastructure to support multimodal AI systems that combine deep learning with language understanding.
Responsibilities:
- Develop a consistent interface for interacting with various LLMs (e.g., OpenAI, DeepSeek, local models).
- Implement prompt routing, fallback strategies, and dynamic model selection to optimize performance and cost.
- Standardize prompt formatting, manage context handling, and monitor token usage across models.
- Support NLP tasks such as summarization, semantic search, classification, and chat interfaces.
- Integrate CNN models for tasks like image classification, object detection, OCR, and visual analysis.
- Combine vision and language models to build multimodal AI pipelines.
- Align model capabilities with product requirements in collaboration with engineering and product teams.
- Design modular and extensible AI infrastructure for fast prototyping and scalable deployment.
- Maintain high standards of code quality, documentation, and reproducibility.