We are looking for a Senior Data Scientist who is a hands-on individual contributor and willing to continue in a technical, delivery-focused role. This is not a managerial track, but a high-impact, strategic role that blends deep technical expertise with business problem-solving.
You will be part of a high-performing analytics team in the FMCG sector , working on a Resource Allocation Model that shapes marketing and media investment decisions, directly impacting sales, consumer engagement, and brand performance.
Location - Bengaluru (onsite)
Notice Period - able to join within 15 to 20 days
Key tasks & accountabilities
- Develop, validate, and scale Resource Allocation Model to quantify the impact of Sales & Marketing packages on sales and brand performance.
- Implement optimization algorithms to inform budget allocation and maximize marketing ROI across geographies and product portfolios.
- Lead the development of predictive and prescriptive models to support commercial, trade, and brand teams.
- Leverage PySpark to manage and transform large-scale retail, media, and consumer datasets.
- Build and deploy ML models using Python and TensorFlow , ensuring robust model performance and business relevance.
- Collaborate with marketing, category, and commercial stakeholders to embed insights into strategic decisions.
- Use GitHub Actions for version control, CI / CD workflows , DVC for data versioning , and reproducible ML pipelines.
- Present findings through compelling data storytelling and dashboards for senior leadership.
- Mentor junior data scientists and contribute to a culture of innovation and excellence.
Qualifications, Experience, Skills
Previous work experience
5+ years of hands-on experience in data science, preferably within the FMCG or retail domain (good to have)Skills required
Proven track record of building and deploying Marketing Mix Models and / or media attribution models.Deep knowledge of optimization techniques (e.g., linear programming, genetic algorithms, constrained optimization).Advanced programming skills in Python (pandas, scikit-learn, statsmodels, TensorFlow).Expertise in PySpark for distributed data processing and transformation.Experience with Git and GitHub Actions for collaborative development and CI / CD pipelines.Strong grounding in statistics, experimental design (A / B testing), and causal inference.Preferred Skills required
Experience working with syndicated retail data (e.g., Nielsen, IRI) and media data (e.g., Meta, Google Ads).Exposure to cloud platforms like AWS , GCP , or Azure .Familiarity with FMCG metrics (e.g., brand health, share of shelf, volume uplift, promotional ROI).Ability to translate complex models into business actions in cross-functional environments.