Who we are
Marketing today is broken in a pretty specific way. Brands have more customer data than ever and they still send the same email to a million people and call it personalization. The decisions about who to talk to, what to offer, and when are still being made by marketers dragging segments in a builder. That's the problem.
Applied Retention sits between a brand's customer data and their CEP (think CleverTap, WebEngage, MoEngage). We pull signals from across warehouses, CRMs, and behavioural data, build an individual-level understanding of every customer, and make the actual decisioning call: right offer, right channel, right moment. Then we pass that decision to the CEP to execute. We don't replace the CEP. We give it a brain.
The category we're building in is AI decisioning for retention and lifecycle marketing. It's a real and growing space globally (Aampe, OfferFit, Monocle) and largely untouched in India. CACs are rising, ROAS is falling, and retention is the only lever left that actually compounds. That's the tailwind. We're building the product that rides it.
The role
This is a founding team hire, which means you're not walking into a defined ML platform with tickets to pick up. You're building the core of what we sell.
You'll work closely with the founding team to design and ship the models that sit at the heart of the product: propensity, intent, next-best-action, uplift. These models need to work on fragmented, imperfect data from real brands, run in production without breaking, and actually move the KPIs our customers care about. That's the bar.
Early on, this is largely an individual contributor role. Over time, as the team grows, you'll have a say in how the ML function is built.
What you'll do
- Design and build customer-level ML models: propensity scoring, intent modelling, next-best-action, uplift.
- Own the full lifecycle: training, deployment, monitoring, retraining.
- Work with real, messy customer data pulled from warehouses, CRMs, and CEPs.
- Run experiments quickly and iterate based on what actually lifts retention metrics.
- Help lay the foundation for how we do ML at Applied Retention as the team scales.
Required
- 3+ years of applied ML with genuine production experience (not just research or notebooks).
- Solid fundamentals across classification, ranking, uplift or recommendation systems.
- Fluent in Python and the core ML stack: scikit-learn, XGBoost or LightGBM, PyTorch.
- Used to working with imperfect, real-world data and making it work anyway.
- Has shipped models that ran in production and kept them running.
Preferred
- Background in decisioning, personalisation, contextual bandits, or causal ML.
- Has worked at an early-stage startup before and knows what that pace feels like.
- Familiar with MLOps tooling: feature stores, experiment tracking, model registries.
- Some exposure to martech, CRM data, or customer behavioural data.
Pay: ₹900,000.00 - ₹1,400,000.00 per year
Work Location: In person
