Generative AI Engineer
Skills
About the role
This is a generative AI engineering role at EaseMyTrip, based in Gurugram, focused on building conversational travel agents powered by large language models. It suits someone with backend development experience who has moved into LLM and NLP work and wants to apply it to travel booking, recommendations and cancellations. The team is building at the intersection of backend systems, AI models and natural language understanding.
What you’ll do
- Integrate LLMs such as GPT-4, Claude and Mistral to process travel queries and generate recommendations
- Design prompts and build retrieval-augmented generation workflows for multi-turn conversations
- Build conversational flows for booking changes and cancellations
- Tune models for latency, scalability and cost
- Build backend services with FastAPI or Django
- Design and manage data in PostgreSQL or MongoDB using ORM tools like SQLAlchemy
- Deploy on AWS, GCP or Azure using containers and serverless functions
- Fine-tune open-source and proprietary LLMs with LoRA and PEFT and evaluate with BLEU/ROUGE
- Build NLP features including entity recognition, sentiment analysis and dialogue state tracking
- Collaborate with AI researchers, frontend engineers and product teams
What they’re looking for
- At least 2 years of backend development experience
- At least 1 year hands-on with LLMs or NLP systems
- Proficiency in Python with async programming and FastAPI or Django
- Experience with LangChain, LlamaIndex, Hugging Face Transformers and OpenAI/Anthropic APIs
- Strong relational and NoSQL database knowledge
- Familiarity with prompt design, LoRA/PEFT fine-tuning and evaluation metrics
- Comfort with cloud platforms and serverless or containerized deployment
- Understanding of intent detection, dialogue management and text classification
What’s on offer
- 8-18 Lacs per annum
Questions about this role
How much experience do I need for this role?
The posting asks for a minimum of 2 years in backend development with at least 1 year working hands-on with LLMs or NLP, and lists 1-4 years overall on the listing.
What does this job pay?
The listed range is 8-18 Lacs per annum.
Where is this job based?
Gurugram, India.
Related roles
AI Engineer – Generative AI
Onsite AI Engineer role in Hyderabad, Ahmedabad, or Indore building generative-AI and agentic systems. The position suits an engineer with at least six years of experience across LLMs, RAG, Python, and cloud deployment.
Generative AI/Agentic AI Engineer
Generative AI and agentic AI engineer role in Noida for a Python developer with four to six years of experience. The position focuses on LLM applications, multi-agent workflows, prompt engineering, RAG, and production integrations.
EXL - Generative AI Engineer - Python/Agentic AI
Generative AI Engineer role developing enterprise LLM, RAG, and agentic-AI solutions in Bangalore. The role suits experienced Python and deep-learning engineers who can take AI systems from experimentation into production.
AI / Generative AI Engineer - Agentic Systems & Platforms - VOIS
Vodafone is hiring a full-time AI / Generative AI Engineer in Pune to build enterprise LLM applications, RAG systems, and agentic workflows. The role suits Python backend engineers with cloud, data, and production AI experience.
AI Engineer Agentic, Generative AI
AI Engineer role in Pune for a Python developer experienced with agentic AI, RAG, LLM integrations, and data workflows. The position combines production software engineering, testing, analytics, and generative AI delivery.
Principal Engineer - Gen AI, LLM, RAG, Agentic AI
A principal engineering role at Wells Fargo in Bengaluru focused on GenAI, RAG and agentic AI architecture, evaluation and governance. Suited to a senior technical leader with deep GenAI stack and AI security expertise.