About the Role

We are seeking a skilled Generative AI Engineer to contribute to our AI innovation team at EaseMyTrip.com. Your role will focus on integrating and optimizing Large Language Models (LLMs) to develop advanced conversational travel agents. These agents will understand, recommend, and assist travelers across various platforms, bringing smart automation to every travel interaction. You will work at the intersection of backend systems, AI models, and natural language understanding to enhance the travel experience.

Key Responsibilities

1. LLM Integration: Deploy and integrate LLMs (e.g., GPT-4, Claude, Mistral) for processing natural language queries and delivering personalized travel recommendations.
2. Prompt Engineering & RAG: Design optimized prompts and implement Retrieval-Augmented Generation (RAG) workflows to improve contextual relevance in multi-turn conversations.
3. Conversational Flow Design: Build and manage robust conversational workflows to handle complex travel scenarios like booking modifications and cancellations.
4. LLM Performance Optimization: Tune models and workflows to achieve a balance of performance, scalability, latency, and cost in diverse environments.
5. Backend Development: Develop scalable, asynchronous backend services using FastAPI or Django, focusing on secure and efficient API architectures.
6. Database & ORM Design: Design and manage data with PostgreSQL or MongoDB, and implement ORM solutions like SQLAlchemy for seamless data interaction.
7. Cloud & Serverless Infrastructure: Deploy solutions on AWS, GCP, or Azure utilizing containerized and serverless tools such as Lambda and Cloud Functions.
8. Model Fine-Tuning & Evaluation: Fine-tune open-source and proprietary LLMs using techniques like LoRA and PEFT, and evaluate outputs with metrics like BLEU and ROUGE.
9. NLP Pipeline Implementation: Develop NLP functionalities including named entity recognition, sentiment analysis, and dialogue state tracking.
10. Cross-Functional Collaboration: Collaborate closely with AI researchers, frontend developers, and product teams to rapidly deliver impactful features iteratively.

Preferred Candidate Profile

1. Experience: Minimum 2 years in backend development with at least 1 year of hands-on experience with LLMs or NLP systems.
2. Programming Skills: Proficiency in Python, with practical experience in asynchronous programming and frameworks like FastAPI or Django.
3. LLM Ecosystem Expertise: Experience with tools and libraries such as LangChain, LlamaIndex, Hugging Face Transformers, and OpenAI/Anthropic APIs.
4. Database Knowledge: Strong understanding of relational and NoSQL databases, including schema design and performance optimization.
5. Model Engineering: Familiarity with prompt design, LLM fine-tuning (LoRA, PEFT), and evaluation metrics for language models.
6. Cloud Deployment: Comfort working with cloud platforms (AWS/GCP/Azure) and building serverless or containerized deployments.
7. NLP Understanding: Solid grasp of NLP concepts including intent detection, dialogue management, and text classification.
8. Problem-Solving Mindset: Ability to translate business problems into AI-first solutions with a user-centric approach.
9. Team Collaboration: Strong communication skills and a collaborative spirit for effective work with multidisciplinary teams.
10. Curiosity and Drive: Passion for staying at the forefront of AI and leveraging emerging technologies to build innovative travel experiences.