Director Data Science

Company Overview : Asper.ai is a cutting-edge AI-based SaaS company focused on revolutionizing enterprise decision making, through demand planning and Revenue growth management for the Consumer-Packaged Goods (CPG) industry. Asper.ai, enables interconnected and automated decisions at the intersection of demand and supply. By changing how decisions are made, Asper.ai unlocks growth and transforms organizations into adaptive, intelligent enterprises.

Job Title : Director / Senior Director Data Science

Exp : 13+ years

Location : Bengaluru

Asper builds agentic AI for Revenue Growth Management and Demand Forecasting at leading global CPG companies. Our agents are only as strong as the models and decision systems behind them. You will lead that foundation: the science, ML engineering, and MLOps behind pricing, promotion, assortment, trade, and demand forecasting decisions that influence billions of dollars in revenue. Your mandate is to make these models scientifically rigorous, production-grade, explainable, and reusable across customers—rather than rebuilding them for every deployment. This is a builder’s role. You will set the technical direction for a multidisciplinary organization while staying close enough to the work to challenge a forecasting methodology, an elasticity estimate, or an optimization approach that may be statistically sound but commercially unusable.

Why work with us?

• Experience a fast paced, growing, and stable start-up with a culture of care at heart. You will be enabled to be your best every day – personally & professionally.
• Be a part of the AI revolution and bring to life solutions that make a difference to the world.
• Coming to work will not feel monotonous – you get to work with some of the brightest and the nicest colleagues you will meet and build bonds for life. We work hard and have fun together as well.

Key Responsibilities :

Understand domain context and conduct exploratory data analysis to determine the best data science approach for the customer.

• Identify how the data science approach can be executed via the product pipeline and any customer specific configurations needed to achieve objectives.
• Train machine learning and deep learning models on large scale time series datasets
• Use data wrangling and exploration to extract insights and relationships from the data
• Perform descriptive analysis and build visualizations to help customer understand what drives the business metrics
• Identify and measure levers to help move essential metrics and make recommendations.
• Perform accuracy analysis to identify opportunities for performance improvement on specific slices of data and ensure high performance across all slices
• Develop end to end automated pipelines for use cases like inventory management, price recommendation, demand forecasting etc.
• Conduct research and prototyping innovations; data and requirements gathering; solution scoping and architecture; consulting clients and clients facing teams on advanced statistical and machine learning problems
• Collaborate and coordinate with different functional teams (engineering and product development) to implement models and monitor outcomes.

Requirements and

• 12+ years of experience in Applied ML, Data Science, or AI.
• 5+ years leading teams that include managers, technical leads, and senior ICs.
• A track record of taking multiple ML products from prototype to production at enterprise scale.
• Deep expertise in time-series and hierarchical forecasting.
• Strong experience in at least one of:
• Pricing and elasticity, Promotion and uplift modelling, Causal inference
• Mathematical optimization
• Strong MLOps experience across model deployment, monitoring, retraining, versioning, and rollback.
• Fluency in Python, SQL, and distributed cloud ML infrastructure.
• The ability to connect model performance to commercial and P&L outcomes.
• Strong communication skills across Product, Engineering, Data Science, and customer executives.

Nice to have

• CPG, retail, supply chain, or Revenue Growth Management experience.
• Experience with econometrics, uplift modeling, reinforcement learning, or advanced optimization.
• Experience integrating predictive models into agentic or LLM-based workflows.
• Familiarity with ontologies, knowledge graphs, or semantic layers.