Data Scientist

IKONZ AI PVT. LTD.
Job Description

Senior Data Scientist
Number of Openings2LocationBhopal, Madhya Pradesh (On-site, Full-Time)Reports ToLead AI EngineerExperience Required4-7 YearsEmployment TypeFull-Time, On-siteDomainAI/ML, Financial Technology
Role Overview
We are hiring Senior Data Scientists to build, train, and deploy production-grade ML models for a large enterprise AI/ML programme in the financial domain. You will work across the full model lifecycle data exploration, feature engineering, model development, validation, deployment, and retraining on complex structured financial datasets. The ideal candidate writes clean production-quality Python, is rigorous about model validation, and has a strong record of delivering ML models that perform reliably on real-world data.
Key Responsibilities

• Design, build, train, and validate ML models across multiple workstreams including: time-series forecasting, transaction anomaly detection, risk scoring, multi-class classification, and clustering on large-scale financial datasets.
• Perform exploratory data analysis (EDA) on enterprise financial data; identify data quality issues and drive remediation.
• Engineer features from raw transactional, vendor, budgetary, and audit data for model training pipelines.
• Select appropriate algorithms and tune hyperparameters to meet agreed accuracy and performance KPIs.
• Produce model accuracy and validation reports: confusion matrices, MAPE/RMSE, F1/precision/recall, risk calibration reports.
• Integrate trained models with the MLOps pipeline (MLflow/Kubeflow); configure automated retraining schedules.
• Implement drift detection; monitor model performance in production and trigger retraining when thresholds are breached.
• Collaborate with Data Engineers on feature pipelines, with Full-Stack developers on model API endpoints, and with the MLOps Engineer on deployment.
• Prepare model governance documentation: data sources, assumptions, accuracy metrics, and retraining methodology.
• Support UAT by providing model explainability outputs and demonstrating model behaviour to business stakeholders.

Required Skills & Experience

• 4-7 years of experience in data science / ML engineering with at least 2 production ML deployments.
• Strong Python: pandas, NumPy, scikit-learn, XGBoost/LightGBM, TensorFlow/PyTorch.
• Time-series forecasting: ARIMA/SARIMA, Facebook Prophet, LSTM hands-on production experience required.
• Anomaly detection and clustering: Isolation Forest, DBSCAN, Autoencoders.
• Classification and risk scoring: logistic regression, random forest, gradient boosting.
• Feature engineering on structured/tabular financial or transactional data.
• MLflow or equivalent for experiment tracking; deploying models as REST APIs (FastAPI/Flask).
• Strong SQL; experience working with Data Warehouses or Data Lakes.
• Production-quality, well-documented Python code not just notebook-level scripts.

Preferred / Good to Have

• Experience with financial data: revenue/expenditure forecasting, transaction monitoring, or vendor/credit risk scoring.
• NLP experience: NER, text classification useful for document AI and chatbot workstreams.
• Familiarity with open-source LLMs and HuggingFace transformers.
• Monte Carlo simulation for risk quantification.
• Exposure to government/PSU or large enterprise ERP-integrated AI/ML projects.

Qualifications

• M.Tech / M.Sc in Data Science, Statistics, Computer Science, AI/ML, or related quantitative field.
• B.Tech with strong ML project portfolio and production deployments also considered.