The Role :

We are looking for a hands-on ML Engineer to build and ship production-grade models that directly impact business metrics. You will own the full lifecycle from wrangling unstructured data and designing features to deploying scalable models on AWS and monitoring real-time performance.

Key Responsibilities :

- Core Modeling: Build and ship models for Personalization, Pricing Optimization, Matchmaking/Ranking, and Fraud Detection.

- NLP & Deep Learning: Leverage embeddings, similarity models, and text classification to drive user profiling and discovery.

- Production Engineering: Collaborate with DevOps to productionize models via APIs, CI/CD, Docker, and AWS/GCP.

- Experimentation: Design and execute A/B tests with strict guardrails and drift monitoring.

Mandatory Qualifications :

- Experience: 2+ years as a Data Scientist or ML Engineer in a Product-based company.

- Exclusion: Please note, we are not seeking candidates from banking, fintech, or traditional financial domains at this time.

Technical Stack :

- Expert Python (Classical ML: Gradient Boosting, Regressions, Decision Trees).

- Hands-on Deep Learning (TensorFlow or PyTorch).

- Domain Depth: Proven experience in at least two of the following:

- Recommendation Systems | Price Modeling | Propensity Models | Fraud/Risk | Image Data.

- NLP Expertise: Strong exposure to text generation/classification, embeddings, and feature extraction from unstructured text.

- Deployment: Practical experience with Docker and cloud environments (AWS/GCP).

Ideal Candidate Profile :

- You are a self-starter who understands that data contracts and feature reliability are just as important as the algorithms themselves.

- You thrive in environments where ML is used to solve high-leverage business problems in real time.