Company Description
Blendis a premier AI services provider, committed to co-creating meaningful impact for its clients through the power of data science, AI, technology, and people. With a mission to fuel bold visions, Blend tackles significant challenges by seamlessly aligning human expertise with artificial intelligence. The company is dedicated to unlocking value and fostering innovation for its clients by harnessing world-class people and data-driven strategy. We believe that the power of people and AI can have a meaningful impact on your world, creating more fulfilling work and projects for our people and clients. For more information, visitwww.blend360.com
Job Description
Own the scientific and delivery backbone of data science engagements: problem structuring, analytical design, modelling strategy, validation framework, and translation of insights into business decisions. You will define what good means analytically, ensure methodological rigor from exploration through deployment, and deliver solutions that are robust, interpretable, and commercially impactful. You will build production-intent analytical solutions and partner with Engineering to operationalise and scale them into enterprise-grade assets.
Client Context
This role will lead the analytical delivery of a sales decomposition engagement, focused on attributing revenue drivers and informing commercial decision-making.
Key Responsibilities
- Translate business challenges into structured analytical problems, testable hypotheses, measurable objectives, and clear scope boundaries (including risks and assumptions).
- Ensure high-quality outputs, adherence to timelines, and proactive management of client expectations.
- Design and execute end-to-end analytical workflows: data sourcing, cleaning, quality control, exploratory analysis, feature engineering, modelling, validation, and insight generation.
- Own the development of retail sales decomposition solutions, selecting appropriate approaches (price and promo elasticity, marketing mix, hierarchical/panel regression, time-series models) to attribute revenue drivers and quantify incremental impact.
- Define evaluation strategies aligned to commercial impact; establish metrics, validation methodology, acceptance thresholds, and robustness standards (cross-validation, sensitivity analysis, bias checks, interpretability) to ensure production-ready deployment.
- Own experimentation and model improvement cycles: structured testing, benchmarking, feature iteration, and performance tracking.
- Deliver production-ready solutions: reproducible code, version-controlled workflows, documentation, monitoring plans, and engineering-ready handoff.
- Clearly articulate modelling assumptions, limitations, and risk considerations to stakeholders.
- Present analytical findings to clients and senior stakeholders, breaking down complex technical concepts into clear, non-technical insights and actionable recommendations.
Qualifications
- 5+ years of commercial experience in data science, applied ML, or advanced analytics.
- Strong background in statistical modelling and commercial analytics, with demonstrated experience delivering end-to-end data science solutions in production environments
- Strong proficiency in Python and major ML frameworks (scikit-learn, PyTorch, TensorFlow).
Required Collaboration Model
- Collaborate with Data Engineering to ensure data quality, pipeline integrity, and readiness for modelling and downstream deployment; support model productionisation, monitoring, and scalability.
- Partner with Senior Data Scientists and broader analytics teams to design, develop, and validate sales decomposition models, contributing to shared modelling standards, documentation, and validation practices.
- Engage Commercial and Product stakeholders throughout delivery to align modelling assumptions, interpret outputs, and inform pricing and trading decisions.
