AI Engineer - Generative AI/LLM
Description
Key Responsibilities :
- Design, develop, and deploy Generative AI and LLM-based applications on Azure.
- Build enterprise-grade Retrieval-Augmented Generation (RAG) solutions.
- Develop end-to-end RAG pipelines including document ingestion, chunking, embeddings, retrieval, reranking, and response generation.
- Work with Azure AI Foundry to develop, evaluate, and deploy AI applications.
- Integrate LLMs and Azure OpenAI with enterprise applications and data sources.
- Implement prompt engineering and optimize prompts for accuracy and reliability.
- Work with vector databases/vector search technologies for semantic retrieval.
- Evaluate LLM and RAG applications for quality, relevance, latency, and cost.
- Develop APIs and services to integrate AI capabilities into business applications.
- Implement monitoring, security, governance, and responsible AI practices.
- Collaborate with data engineers, software engineers, architects, and business teams to deliver production-ready AI solutions.
Required Skills :
- 8 to 15 years of experience in software engineering, AI/ML engineering, or related fields.
- Strong hands-on experience with Azure AI Foundry.
- Strong experience with Generative AI and LLMs.
- Hands-on experience designing and implementing RAG architectures.
- Experience with Azure OpenAI / LLM APIs.
- Strong Python programming skills.
- Experience with embeddings, vector search/vector databases, and semantic retrieval.
- Good understanding of prompt engineering and LLM evaluation.
- Experience building and deploying production-grade AI applications.
- Strong understanding of Azure cloud services and AI architecture.