Senior Data Scientist

PRICELINE CAREERS; Mumbai; Hybrid; INR 1,000,000 - 2,000,000; Full time

Job summary

PRICELINE CAREERS is hiring a Senior Data Scientist in Mumbai, India. In this hybrid role, you will leverage your expertise in machine learning and data analysis to design and implement models that will transform hotel content decision-making. You will work closely with various teams to integrate these models, aiming to enhance booking rates globally. The ideal candidate holds a Masters or PhD, possesses over 5 years of relevant experience, and is adept in programming languages like Python and SQL.

Qualifications

• 5+ years experience in building and productionizing ML models
• Proficient in Python and SQL for data analysis
• Hands-on experience with NLP techniques required

Responsibilities

• Translate business questions into ML problems.
• Build content scoring and ranking models.
• Design and test optimization strategies for content.

Skills

ML model building

Data analysis

NLP techniques

Python

SQL

Cloud platforms

Education

Masters or PhD in a quantitative field

Tools

Google Cloud Platform

Apache Airflow

Tableau

Job description

Senior Data Scientist

This role is eligible for our hybrid work model: Two days in-office.

We’re a data-driven organization, which makes our Analytics and Data Science teams the brains of our operation. On the cutting edge of customer and business analytics, they make sure all our decisions and innovations are based on the latest insights.

Why this job’s a big deal:

Priceline's Hotel Content Product Group is transforming how millions of travelers experience hotel listings — moving from static property pages to dynamic, personalized storefronts that surface the right content at the right time. As a Senior Data Scientist on this team, you'll be the architect behind that transformation. You'll build models that determine which images, amenities, review highlights, and page layouts drive conversions — across property, room, and rate levels — and you'll define the success metrics and scalability strategy to automate those decisions across millions of hotels worldwide.

In this role you will get to:

Translate ambiguous business and product questions into well-defined ML problems, and identify the signals and features that matter most.

Build content scoring and ranking models that determine image relevance, amenity hierarchy, and review highlight selection to maximize conversion.

Develop NLP models to extract and surface the most impactful guest review snippets for each property.

Evaluate and iterate on GenAI applications for hotel content intelligence, including judgment model design, quality scoring, and cost/quality tradeoff analysis.

Design and test layout optimization strategies for the Property Details Page, including section ordering by property type (e.g., city hotels vs. resorts) and platform (app vs. desktop).

Solve content personalization challenges across three hierarchy levels: property-level differentiation, room-level comparison, and rate-level value communication.

Define success metrics that connect content decisions to measurable business outcomes such as booking velocity, engagement, and conversion rate.

Own models end-to-end — from development through production monitoring — and design the outcome logic that translates raw model scores into user-facing product features (e.g., badges, review keyword highlights, ranked content modules).

Partner with Data, Product, and Technology teams to integrate model output with transactional systems, and build prototypes to demonstrate the impact of proposed changes to content decision systems.

Who you are:

Masters or PhD degree in a quantitative or computational field (i.e., Math, Statistics, Operations Research, Computer Science, or Physics)

5+ years experience building and productionizing statistical and machine learning models

Proficient in a programming language used for data analysis (R/Python) and query knowledge (SQL)

Comfortable working on high-velocity structured and unstructured data.

Hands-on experience with NLP techniques (text classification, entity extraction, sentiment analysis, or similar)

Experience with ML computing on cloud platforms, with preference for Google Cloud Platform and Vertex AI (AWS or Microsoft Azure experience also considered)

Experience with developing, scheduling, and monitoring batch-oriented workflows through platforms like Apache Airflow, Kubeflow, etc.

Familiarity with data analysis, modeling, and visualization tools such as R and/or Python, Jupyter, SQL, Hadoop, and Tableau

Illustrated history of living the values necessary to Priceline: Customer, Innovation, Team, Accountability and Trust.

The Right Results, the Right Way is not just a motto at Priceline; it’s a way of life. Unquestionable integrity and ethics is essential.