About the Role:
We are looking for a talented Generative AI Engineer to join our AI innovation team at EaseMyTrip.com and help power the next generation of intelligent travel experiences. In this role, you will lead the integration and optimization of Large Language Models (LLMs) to create conversational travel agents that can understand, recommend, and assist travelers across platforms. You will work at the intersection of backend systems, AI models, and natural language understanding, bringing smart automation to every travel interaction.
Key Responsibilities:
- LLM Integration: Deploy and integrate LLMs (e.g., GPT-4, Claude, Mistral) to process natural language queries and deliver personalized travel recommendations.
- Prompt Engineering & RAG: Design optimized prompts and implement Retrieval-Augmented Generation (RAG) workflows to enhance contextual relevance in multi-turn conversations.
- Conversational Flow Design: Build and manage robust conversational workflows capable of handling complex travel scenarios such as booking modifications and cancellations.
- LLM Performance Optimization: Tune models and workflows to balance performance, scalability, latency, and cost across diverse environments.
- Backend Development: Develop scalable, asynchronous backend services using FastAPI or Django, with a focus on secure and productive API architectures.
- Database & ORM Design: Design and manage data using PostgreSQL or MongoDB, and implement ORM solutions like SQLAlchemy for seamless data interaction.
- Cloud & Serverless Infrastructure: Deploy solutions on AWS, GCP, or Azure using containerized and serverless tools such as Lambda and Cloud Functions.
- Model Fine-Tuning & Evaluation: Fine-tune open-source and proprietary LLMs using techniques like LoRA and PEFT, and evaluate outputs using BLEU, ROUGE, or similar metrics.
- NLP Pipeline Implementation: Develop NLP functionalities including named entity recognition, sentiment analysis, and dialogue state tracking.
- Cro