We are seeking a passionate and experienced AI/ML Engineer with at least 5 years of hands-on experience in Generative AI, Retrieval-Augmented Generation (RAG), LangChain, and modern search database technologies (at least one of Elasticsearch, OpenSearch, Vespa, or Weaviate is mandatory).

The ideal candidate will play a key role in designing and deploying intelligent systems that combine large language models (LLMs) with efficient document retrieval and indexing pipelines.

Responsibilities :

- Design, develop, and deploy AI/ML solutions using state-of-the-art Generative AI models (GPT, Claude, LLaMA, etc.)

- Implement and optimize RAG pipelines using LangChain or similar frameworks.

- Develop connectors for ingestion, indexing, and semantic search using Elasticsearch, OpenSearch, Vespa, or Weaviate.

- Build and maintain vector stores and document indexing pipelines for performant, context-aware information retrieval.

- Collaborate with cross-functional teams to integrate GenAI features into products and services.

- Monitor model performance and continuously improve retrieval and generation accuracy.

- Evaluate and fine-tune open-source and proprietary LLMs as needed.

- Document best practices, architecture decisions, and technical guides.