Job Title: ML / LLM Engineer – Travel Intelligence Platform

Location: Noida sec 62

Employment Type: Full time

Experience Level: 3+ yrs

About the Company

We are building an AI-driven travel platform designed to generate highly personalized itineraries using our large structured travel database. Our mission is to redefine how people plan their journeys by combining advanced machine learning with rich global tourism data.

About the Role

We are looking for an ML / LLM Engineer to architect and build the core intelligence layer of our travel platform. Our system separates the ML Decision Engine (responsible for all decision-making, optimization, and learning) from the LLM API Layer (used exclusively for natural language interaction).

You will be responsible for ensuring the ML layer drives all business logic while the LLM layer handles conversational responses and itinerary descriptions — without overriding core intelligence.

Key ResponsibilitiesLLM Integration & Orchestration

• Integrate LLM APIs (OpenAI / Claude / Llama / Mistral)
• Design structured prompt templates for consistent responses
• Build and optimize RAG (Retrieval-Augmented Generation) pipelines
• Ensure LLM outputs do not override core ML business logic
• Convert structured itinerary JSON into natural, user-friendly language
• Handle real-time conversational trip modifications
ML & Decision Engine

• Develop and optimize recommendation systems
• Build multi-parameter scoring models for personalization
• Implement optimization algorithms for itinerary planning
• Work with geospatial data for location-based decision-making
Backend & Infrastructure

• Build and maintain AI APIs for seamless integration
• Deploy and scale AI systems on cloud platforms
• Ensure system reliability, performance, and scalability

Technical RequirementsCore ML Skills

• Strong proficiency in Python
• Hands-on experience with Scikit-learn
• Experience with TensorFlow or PyTorch
• Proven experience in recommendation systems
• Strong understanding of optimization algorithms
• Experience building multi-parameter scoring models
LLM & AI Stack

• Experience integrating OpenAI / Claude / Llama APIs
• Deep understanding of prompt engineering
• Strong knowledge of RAG architectures
• Experience with LangChain or LlamaIndex
• Ability to enforce structured output control
• Experience with embeddings generation
• Hands-on experience with vector databases (FAISS, Pinecone, Weaviate, etc.)
Backend & Infrastructure

• Experience building AI APIs in production
• Familiarity with FastAPI or Flask
• Working knowledge of Docker for containerization
• Cloud deployment experience (AWS / GCP / Azure)
• Understanding of scaling AI systems for real-time use

Preferred Qualifications

• Prior experience in recommendation engines
• Background in travel / hospitality platforms
• Knowledge of geospatial optimization
• Experience handling large structured datasets
• Understanding of reinforcement learning or adaptive systems

What We’re Looking For

• Strong system architecture mindset
• Ability to separate ML logic from LLM generation
• Experience building production-ready AI systems
• Excellent problem-solving skills
• Ability to design scalable learning pipelines
• A collaborative team player who thrives in a fast-paced environment

Why Join Us?

• Work on cutting-edge AI technology in the travel domain
• Architect and own the core intelligence layer from day one
• Be part of a high-growth, innovation-driven team
• Direct impact on product direction and AI capabilities