Data Scientist

Mirchi; Dadri; On-site; INR 1,800,000 - 2,400,000; Full time

Job summary

Mirchi is seeking an experienced ML engineer to design and optimize personalized recommendation systems and search relevance for its music platform. You will work on real-time and batch pipelines, aiming to boost engagement and content discovery.

The role requires deep expertise in ML, data modeling, and scalable infrastructure, with strong Python/SQL skills and experience with large-scale data systems. You will collaborate across teams to translate insights into product growth.

Qualifications

• 7+ years of work experience with Master’s degree in Computer Science, Mathematics or a related field.
• Hands-on experience with Recommendation systems and Search ranking (Elasticsearch, vector search, embeddings).
• Predictive modeling techniques.
• Solid understanding of Machine Learning algorithms, Statistics & probability, Feature engineering & model evaluation.
• Strong proficiency in Python & SQL.
• Experience with data visualization tools.
• Experience with SQL and large-scale data systems (BigQuery, Spark).
• Familiarity with real-time data processing.
• Exposure to MLOps and deployment pipelines.
• Strong problem-solving and analytical thinking.
• Ability to communicate complex findings to non-technical stakeholders.
• High attention to detail and data accuracy.
• Collaborative mindset and ability to work in cross-functional teams.

Responsibilities

• Design and optimize personalized recommendation engines.
• Build real-time and batch recommendation pipelines for playlists, songs, and content discovery.
• Improve CTR, session time, and content consumption through personalization.
• Develop and enhance search relevance and ranking algorithms.
• Work on query understanding, typo correction, intent detection, and semantic search.
• Optimize search-to-play conversion and reduce zero-result scenarios.
• Build models for churn prediction, user lifetime value, conversion propensity, and cohort management.
• Drive proactive interventions using predictions.
• Design and run A/B tests and multivariate experiments.
• Measure impact using key metrics.
• Translate data insights into product and growth strategies.
• Collaborate with engineering to productionize models and monitor performance.

Skills

Python

SQL

Recommendation systems

Search ranking

ML algorithms

Statistics & probability

Feature engineering

MLOps

Data visualization

Communication to stakeholders

Cross-functional teamwork

Education

Master’s degree in Computer Science, Mathematics or a related field

Tools

Elasticsearch

BigQuery

Spark

Vector search

Job description

• Design and optimize personalized recommendation engines (collaborative filtering, content-based, hybrid models)
• Build real-time and batch recommendation pipelines for playlists, songs, and content discovery
• Improve CTR, session time, and content consumption through personalization

2. Search & Ranking

• Develop and enhance search relevance and ranking algorithms
• Work on query understanding, typo correction, intent detection, and semantic search etc
• Optimize search-to-play conversion and reduce zero-result scenarios
• Build models for Churn prediction, User lifetime value (LTV), Conversion propensity, Cohort Management
• Drive proactive interventions using predictions
• Design and run A/B tests and multivariate experiments
• Measure impact using key metrics
• Translate data insights into product and growth strategies

5. Data & ML Infrastructure

• Work with large-scale datasets to build scalable ML pipelines
• Collaborate with engineering teams to productionize models
• Monitor model performance and continuously iterate

Required Qualifications

• 7+ years of work experience with Master’s degree in Computer Science, Mathematics or a related field
• Hands-on experience with Recommendation systems, Search ranking (Elasticsearch, vector search, embeddings)
• Predictive modeling techniques
• Solid understanding of Machine Learning algorithms, Statistics & probability, Feature engineering & model evaluation
• Strong proficiency in Python & SQL
• Experience with data visualization tools
• Experience with SQL and large-scale data systems (BigQuery, Spark, etc.)
• Familiarity with real-time data processing
• Exposure to MLOps and deployment pipelines
• Strong problem-solving and analytical thinking
• Ability to communicate complex findings to non-technical stakeholders
• High attention to detail and data accuracy
• Collaborative mindset and ability to work in cross-functional teams