Ai Ml Engineer

About Role:

We are looking for an AI/ML Engineer to join our data & analytics team at Fintech Cloud.

The role involves building machine learning models on loan and collections data across our multi-brand lending portfolio including credit risk scoring, NPA/default prediction, collections prioritization, and customer behavior modeling. You will work closely with the data engineering and analytics teams and take models from experimentation through to production deployment.

Mandatory Requirements:

• 2-3 years of minimum hands-on experience in an AI/ML or Data Science role.
• Prior experience working in a fintech, NBFC, banking, or lending environment is a must.
• Strong proficiency in SQL complex joins, window functions, query optimization on large datasets.
• Strong proficiency in Python Pandas, NumPy, and standard data manipulation workflows.

AI/ML Skills & Experience

• Solid grounding in statistics and ML fundamentals: probability, hypothesis testing, feature engineering, bias-variance tradeoff.
• Hands-on experience with ML algorithms: Logistic Regression, Decision Trees, Random Forest, XGBoost/LightGBM, clustering.
• Experience with scikit-learn and at least one deep learning framework (TensorFlow or PyTorch) is a plus.
• Understanding of model evaluation metrics: AUC-ROC, precision/recall, F1, KS-statistic, population stability index (PSI) especially relevant for credit risk models.
• Experience handling imbalanced datasets and cold-start problems (common in NPA/default prediction).
• Working knowledge of model deployment Flask/FastAPI APIs, or deploying models on cloud platforms (GCP/AWS/Databricks).
• Familiarity with BigQuery or similar cloud data warehouses for feature extraction at scale.
• Working knowledge of cloud platforms AWS and/or GCP (compute, storage, basic deployment services like EC2/Cloud Run, S3/GCS).
• Basic software engineering knowledge Git/version control, writing clean modular code, REST APIs, and working comfortably in a Linux environment.
• Exposure to MLOps basics — model versioning, monitoring drift, retraining pipelines.
• Bonus: exposure to NLP or LLM-based applications (chatbots, document extraction, GenAI use-cases).

Key Responsibilities

• Design, build, and validate ML models for credit risk scoring, NPA/DPD prediction, and collections optimization.
• Work with large-scale loan and transactional data across 30+ lending brands in BigQuery/Databricks.
• Partner with the data engineering team to build reliable feature pipelines for model training and scoring.
• Deploy models into production (Flask APIs / batch scoring pipelines) and monitor performance over time.
• Translate business problems from Risk, Collections, and Credit teams into ML solutions.
• Document model logic, assumptions, and performance for internal and audit/compliance review.