Location Name: Pune Corporate Office - Weikfield
Job Purpose
To build, and scale advanced Real-Time Approval and Analytics-driven Decisioning systems that enable high-speed, data-powered customer acquisition at enterprise scale. This role is responsible for leading the design and deployment of standardized, product-specific approval engines using machine learning, real-time data pipelines, and automation frameworks. Acting as a technical owner, the role ensures low-latency, high-accuracy decisioning while continuously optimizing customer journeys, funnel performance, and approval efficiency. The primary objective is to institutionalize robust, scalable, and production-ready data science solutions that eliminate operational friction and accelerate business growth aligned with LRS financial objectives.
Duties And Responsibilities
Data Analytical Solution Development
- Act as the primary analytics and decisioning lead interfacing between Business/COEs, Product, Data Engineering, and Technology teams to translate business vision into scalable Real-Time Approval and ML-driven decisioning solutions.
- Own end-to-end solution design for assigned product streams by reviewing business user stories, conducting gap analysis, and driving creation of architecture blueprints, analytical approach documents, and data flow designs in collaboration with engineering teams.
- Lead decomposition of complex business and regulatory requirements into structured analytical workflows, model specifications, feature engineering requirements, and measurable business outcomes.
- Govern enrichment by embedding customer-centric design, standardization principles, reusability frameworks, and horizontal scalability across product lines.
- Review and approve technical and data solutioning documents to ensure alignment with approved BRDs, model governance standards, latency SLAs, and production-readiness criteria.
- Drive end-to-end integration coverage across upstream data sources, real-time processing layers, model inference services, and downstream business systems.
- Define and oversee data ecosystem architecture including feature store strategy, real-time ingestion pipelines, model deployment patterns, and monitoring frameworks supporting the RT Approval Engine.
- Mentor junior data scientists and analysts on solution design, modeling best practices, and business context to build strong analytical capability within the team.
- Proactively identify platform enhancement opportunities using performance analytics, funnel insights, and experimentation results and prioritize initiatives based on business impact.
- Track emerging technologies in real-time analytics, ML platforms, and decisioning engines and recommend adoption strategies aligned with organizational roadmap.
- Represent the analytics and data science charter in product governance forums, roadmap discussions, quarterly planning sessions, and leadership reviews.|
- Own definition of critical success metrics including business KPIs, model accuracy, latency SLAs, stability thresholds, and automation efficiency prior to production rollout.
- Establish continuous performance monitoring frameworks post-launch to ensure sustained SLA compliance, model reliability, and business outcome realization.
Project Management and control
Lead intake, prioritization, and execution planning of analytics, ML, and integration requirements from COEs across multiple concurrent initiatives.
Conduct competitive benchmarking and industry trend analysis to guide roadmap decisions and product evolution.
Own consolidated delivery trackers and executive dashboards for leadership reporting on milestones, risks, dependencies, and value realization.
Coordinate cross-functional delivery squads including engineering, QA, platform, and business stakeholders to ensure on-time and high-quality releases.
Lead UAT validation efforts for Real-Time Approval Engine use cases including rule logic validation, model performance testing, and end-to-end journey verification.
Review and approve business use cases from feasibility, scalability, and long-term maintainability perspectives.
Ensure architectural simplicity, modularity, and scalability while maintaining enterprise-grade performance and reliability standards.
Post Product release maintenance and support
Own post-release performance governance across application stability, data pipelines, ML models, and business KPIs.
Ensure real-time data movement, feature freshness, and SLA adherence across ingestion, transformation, and inference layers.
Lead root cause analysis for production issues, performance degradation, and model drift, driving corrective action plans.
Oversee impact assessments for platform changes, enhancement releases, and model upgrades to minimize business disruption.
Monitor end-to-end funnel performance, approval turnaround time, drop-off rates, and pre/post approval experience metrics.
Design and supervise experimentation frameworks including A/B testing, pilot rollouts, and controlled releases to measure business uplift.
Drive continuous optimization cycles by refining decision logic, retraining models, tuning rules engines, and improving automation workflows.
Key Decisions / Dimensions
Following Decisions Are Taken By The Role
Acceptance and Rejection of Business use cases based on system capabilities and cost required to develop the feature.
Project task prioritization based on management and leadership view.
Collecting signoffs and Go live plan from Business/COE Heads.
Major Challenges
Changing scope of project by business/COE leads to lot of rework.
Upskilling on system compatibilities and capabilities w.r.t Loan approval workflows.
Tech debt and legacy systems, change management and performance related challenges
Clear visibility on data flow from core systems to ancillary applications in Real time.
Required Qualifications And Experience
Post Graduate/Graduate degree in Data Science, Machine Learning, Computer Science, Statistics, Applied Mathematics, Engineering, or related quantitative disciplines.
Professional certifications in Cloud Platforms, ML Engineering, Data Engineering, or Product Analytics will be an added advantage.
- Work Experience
- 47 years of relevant experience across data science, advanced analytics, ML-driven product development, digital lending platforms, or real-time decisioning systems.
- Strong experience working at the intersection of data science, product engineering, and business stakeholders to deliver scalable analytics solutions.
- Deep understanding of real-time data processing systems, loan management systems (LMS), financial platforms, and BFSI digital ecosystems.
- Hands-on expertise in:
oMachine learning model development, validation, deployment, and monitoring
oReal-time inference pipelines and API-based model serving
oFeature engineering, feature store design, and data pipeline optimization
oFunnel analytics, customer journey analysis, and campaign performance optimization
- Proven ability to lead pre-product research, solution prototyping, experimentation (A/B testing), and rapid iteration cycles.
- Experience with cloud-based data platforms, distributed computing frameworks, and ML lifecycle management tools (MLflow, CI/CD pipelines, model registries).
- Strong knowledge of model governance, explainability frameworks, bias monitoring, performance tracking, and regulatory compliance requirements in BFSI environments.
- Demonstrated capability to mentor junior team members, review technical deliverables, and guide best practices adoption.
- Strong stakeholder management, communication, and solution storytelling skills to influence product decisions and leadership alignment.
- Ability to manage multiple concurrent initiatives, balance delivery timelines, and drive outcome-oriented execution.
