Overview
Design, build and deploy Generative AI applications using large language models, including RAG pipelines, chatbots and intelligent automation.
What you'll do
- Design, develop, and deploy Generative AI applications using LLMs.
- Build and optimize Retrieval-Augmented Generation (RAG) pipelines.
- Integrate LLM APIs such as OpenAI, Gemini, Claude, or open-source models.
- Develop and implement prompt engineering techniques to improve AI responses.
- Build AI-powered chatbots, virtual assistants, and intelligent automation solutions.
- Work with vector databases for embedding storage and semantic search.
- Develop scalable AI workflows using frameworks such as LangChain and LlamaIndex.
- Fine-tune and evaluate language models based on business requirements.
- Collaborate with software engineers, data scientists, and product teams.
- Optimize model performance, response accuracy, latency, and cost.
- Implement testing, monitoring, and evaluation frameworks for AI applications.
- Ensure responsible AI practices, data privacy, and security.
What you'll need
- Strong programming knowledge of Python.
- Hands-on experience with Generative AI and Large Language Models (LLMs).
- Knowledge of Prompt Engineering and Context Engineering.
- Experience with OpenAI API, Gemini, Claude, or Hugging Face.
- Understanding of Retrieval-Augmented Generation (RAG).
- Experience with LangChain or LlamaIndex.
- Knowledge of Vector Databases such as Pinecone, FAISS, ChromaDB, or Weaviate.
- Understanding of Machine Learning and Deep Learning fundamentals.
- Knowledge of NLP, embeddings, and semantic search.
- Experience with REST APIs and FastAPI or Flask.
- Familiarity with Git, Docker, and cloud platforms (AWS/Azure/GCP).
Details
- Location: Noida, Uttar Pradesh, India.
Read the full description and apply on the company’s own careers page.