NeGD is currently inviting applications for the Senior Data Scientist position on a contractual basis, initially for three years, with possible extensions based on project requirements.

Responsibilities

• Collaborate with domain experts and programme stakeholders to translate policy and business requirements into mathematical formulations and machine learning problem statements; define target variables, feature spaces, evaluation datasets and success criteria.
• Construct peer-group and cohort baselines from live portfolio data where no fixed threshold exists, so that a declared technical, financial or operational value can be assessed as plausible or implausible relative to genuinely comparable cases.
• Design and implement anomaly and outlier detection models on declared and transactional data using isolation forests, local outlier factor, one-class methods, robust z-score and MAD techniques, density and mixture models, autoencoder-based detection, and change-point detection for implausible shifts across successive submissions.
• Build duplication, entity-resolution and network-analysis models to detect linked claims, repeat beneficiaries and collusive patterns across applicant, beneficiary, payment and verification records.
• Develop supervised predictive models for operational and process risk – including probability of timeline or service-level breach for in-flight cases from queue depth, case complexity, reviewer workload, case type and historical processing-time distributions – and calibrate outputs so that a predicted score is interpretable as a probability.
• Develop time-series and probabilistic forecasting models for generation, demand, capacity, congestion and workload, covering short-term, day-ahead and longer horizons, with rolling origin backtesting and horizon-wise error reporting.
• Build structured and econometric models for price, tariff and cost-band prediction, scenario simulation across alternative configurations, and conversion or viability probability scoring, with explainable reasoning traces for decision-making officers.
• Perform unsupervised pattern mining at portfolio scale to surface behavioural deviation across reviewing entities, regional disparities, temporal and seasonal patterns and capacity imbalances, applying stratification or propensity adjustment to control for case mix and correcting for multiple comparisons before any signal is surfaced.
• Design, train and improve computer vision models on high-resolution satellite, aerial and drone imagery – semantic segmentation, object detection, sizing and change detection – for asset identification, installation verification and resource potential mapping; design ground-truth capture and active-learning strategies to extend coverage across site types and environmental conditions.
• Build and maintain feature and data pipelines over structured, semi-structured, geospatial, imagery and document-derived data, including data quality assessment, labelling, de-duplication, and screening to separate non-personal data from personal data requiring protected handling.
• Design and execute comprehensive model evaluation frameworks including cross-validation strategy, statistical significance testing, operating-point selection on the precision-recall curve, false-positive budgeting against available human review capacity, and custom domain metrics.
• Analyse model interpretability and explainability using SHAP values, LIME, counterfactual explanation, partial dependence and gradient-based attribution, and translate model output into a written basis that a reviewing officer or auditor can act on.
• Establish drift detection, retraining triggers and periodic re-validation; perform error analysis and failure-mode identification; and document model architecture, assumptions, known limitations, lineage and version history.
• Conduct bias and fairness evaluation on all models, and ensure compliance with the Digital Personal Data Protection Act 2023, MeitY’s Responsible AI guidelines, Government of India data classification policy and data residency requirements.
• Mentor junior data scientists and analysts on statistical method, experimental design and evaluation discipline; conduct code and model reviews; and contribute to internal capability building.
• Document findings and present model behaviour, limitations and results to programme leadership, ministry stakeholders and technical review forums; contribute to technical reports, standards and reusable methodology.
• Contribute to other NeGD projects as assigned.

Important Links

About National e-Governance Division (NeGD)

The National e-Governance Division (NeGD) is an independent business division under the Digital India Corporation, Ministry of Electronics and Information Technology. NeGD has been playing a pivotal role in supporting MeitY in Programme Management and implementation of e-Governance projects and initiatives undertaken by various Ministries/ Departments, both at the Central and State levels.

NeGD has been spearheading several innovative initiatives under the aegis of the Digital India Programme. Those have been developed keeping the vision areas of Digital India at the core- providing digital infrastructure as a core utility to every citizen, governance and services on demand and in particular, digital empowerment of the citizens of our country; some of these initiatives include DigiLocker, UMANG, Poshan Tracker, OpenForge Platform, API Setu, National Academic Depository, Academic Bank of Credits, Learning Management System.