Description

You will design and implement generative AI solutions using LLMs and RAG architectures.

This role is hybrid.

Responsibilities

• Design and implement GenAI solutions using LLMs such as OpenAI, Claude, Gemini, or LLaMA.
• Build RAG pipelines by integrating LLMs with search databases and vector stores.
• Implement document indexing, embedding generation, and retrieval workflows.
• Develop scalable, secure APIs to serve GenAI use cases.
• Optimize prompt engineering and fine-tune LLM performance using feedback and usage metrics.

Required Skills

• 5+ years of experience in AI or ML development.
• Hands-on experience with GenAI and LangChain.
• Proficiency with vector databases such as FAISS, Chroma, or Pinecone.
• Experience with search databases like Elasticsearch, OpenSearch, Vespa, or Weaviate.
• Ability to preprocess structured and unstructured datasets for LLM consumption.
• Any Graduate degree.

Key Skills

Education

Any Graduate