Generative AI Engineer

EaseMyTrip.com is seeking a dynamic Generative AI Engineer to join its AI innovation team in Gurgaon/Gurugram. This role is pivotal in developing the next generation of intelligent travel experiences by integrating and optimizing Large Language Models (LLMs). You will be instrumental in creating conversational travel agents capable of understanding traveler needs, providing recommendations, and offering assistance across various platforms. This position operates at the nexus of backend systems, advanced AI models, and natural language understanding to automate and enhance every aspect of the travel journey.

Key Responsibilities:

• LLM Deployment: Integrate and deploy LLMs such as GPT-4, Claude, and Mistral to interpret natural language queries and deliver tailored travel recommendations.
• Prompt Engineering and RAG: Develop sophisticated prompts and implement Retrieval-Augmented Generation (RAG) frameworks to ensure contextual accuracy in extended conversations.
• Conversational AI Design: Engineer and maintain robust conversational flows to manage complex travel scenarios, including modifications and cancellations.
• Performance Optimization: Fine-tune LLM models and workflows for optimal balance between performance, scalability, latency, and cost-effectiveness.
• Backend Service Development: Build scalable, asynchronous backend services using Python frameworks like FastAPI or Django, emphasizing secure and efficient API design.
• Data Management: Design and manage data with PostgreSQL or MongoDB, utilizing ORM solutions like SQLAlchemy for streamlined data interaction.
• Cloud Infrastructure: Deploy solutions on major cloud platforms (AWS, GCP, Azure) using containerization and serverless technologies (e.g., Lambda, Cloud Functions).
• Model Fine-Tuning: Adapt open-source and proprietary LLMs using methods like LoRA and PEFT, and evaluate performance with metrics such as BLEU and ROUGE.
• NLP Functionality: Implement core NLP capabilities, including named entity recognition, sentiment analysis, and dialogue state tracking.
• Team Collaboration: Foster close collaboration with AI researchers, frontend developers, and product managers to rapidly deliver innovative features.

Ideal Candidate Profile:

• A minimum of 2 years in backend development, with at least 1 year of direct experience with LLMs or NLP systems.
• Proficiency in Python, including asynchronous programming and experience with FastAPI or Django.
• Hands-on experience with the LLM ecosystem, including tools like LangChain, LlamaIndex, Hugging Face Transformers, and APIs from OpenAI/Anthropic.
• Solid understanding of relational and NoSQL databases, schema design, and performance tuning.
• Familiarity with prompt design, LLM fine-tuning techniques (LoRA, PEFT), and language model evaluation.
• Experience deploying applications on cloud platforms (AWS, GCP, Azure) using serverless or containerized architectures.
• Strong foundational knowledge of NLP concepts such as intent detection, dialogue management, and text classification.
• A strategic problem-solver with the ability to translate business needs into effective AI-driven solutions.
• Excellent communication and teamwork skills for effective cross-functional collaboration.
• A passion for AI advancements and a drive to leverage emerging technologies for innovative travel solutions.