Job Opportunities API

About CodeNinja CodeNinja is a full-stack AI delivery company that helps enterprises, governments, and software acquirers build and operate intelligence-driven systems for mission-critical workflows. We specialize in deploying AI into real operations—combining strong engineering fundamentals with AI-native delivery to create measurable value, resilience, and long-term ownership for our clients. Our global footprint and delivery model are supported by AI Labs, AI Pods, and Global Capability Centers, enabling teams to co-engineer scalable platforms across regions and time zones. Role Overview We are seeking a Senior Machine Learning Engineer (Lead) with 5–6 years of experience to architect, develop, and lead advanced time-series forecasting solutions for high-impact financial use cases. This role requires deep technical expertise in machine learning, strong financial domain knowledge, and the ability to translate research-driven models into production-grade systems within mission-critical environments. You will play a pivotal role in building robust, interpretable, and scalable forecasting models supporting financial risk management, FX exposure, treasury planning, and multi-entity forecasting. Key Responsibilities 1. Technical Leadership & Model Development Lead end-to-end development of time-series forecasting solutions — from data acquisition and feature engineering to deployment and monitoring. Architect scalable ML pipelines tailored for financial forecasting use cases. Develop and benchmark classical statistical models (ARIMA, SARIMA, ETS) alongside ML approaches (XGBoost, Gradient Boosting, Prophet, etc.). Design advanced time-series features including lag structures, rolling statistics, seasonal/trend decomposition, Fourier terms, regime indicators, and exogenous variable integration. Implement time-aware cross-validation strategies and Bayesian hyperparameter optimization. Conduct rigorous backtesting aligned with financial validation methodologies. 2. Financial Modeling & Risk Analytics Build forecasting models for: FX exposure forecasting Treasury cash flow prediction Intercompany netting optimization Financial risk modeling Multi-currency and multi-entity forecasting Quantify model uncertainty and incorporate confidence intervals for financial decision-making. Perform anomaly detection and outlier analysis in financial time-series datasets. Ensure models align with financial reporting cycles, treasury constraints, and accounting standards. 3. Production Deployment & MLOps Design reproducible ML workflows and production-ready pipelines. Implement model versioning, monitoring, drift detection, and automated retraining strategies. Collaborate with engineering teams to deploy solutions in cloud environments. Build business-facing dashboards (Streamlit, Tableau, Power BI). Ensure model governance, documentation, and auditability standards are maintained. 4. Collaboration & Mentorship Translate complex technical insights into actionable business narratives. Partner with Finance, Treasury, Risk, and Executive stakeholders. Mentor junior ML engineers and establish best practices in feature engineering, validation, and interpretability. Promote technical excellence and maintain high code quality standards. Requirements 5–6 years of hands-on ML engineering experience with strong expertise in time-series forecasting. Proven experience in financial domain use cases (FX forecasting, treasury operations, financial risk modeling, etc.). Deep understanding of time-series feature engineering (lags, rolling aggregates, decomposition, exogenous drivers). Experience with classical statistical forecasting models (ARIMA, SARIMA, Exponential Smoothing). Strong Python proficiency (pandas, NumPy, scikit-learn, XGBoost). Experience with Prophet or comparable forecasting frameworks. Expertise in: