Sr. Data Scientist

Quince; Bengaluru; On-site; INR 1,400,000 - 2,400,000; Full time

Job summary

Quince in Bangalore seeks a Senior Data Scientist to advance supply chain planning through operations research, optimization, and AI-native modelling. You will own end-to-end modelling across routing, inventory, and network optimization, collaborating with teams in Bangalore and Palo Alto to productionize solutions with measurable impact.

The role emphasizes producing robust models, deploying them to production, and continuously improving them with data-driven experimentation and

Qualifications

• 5-8 years in operations research, data science, applied mathematics, industrial engineering, or a related quantitative field.
• Demonstrated experience building and deploying production models that have delivered measurable business impact.
• Strong expertise in optimization methodologies, including LP, MIP, CP, heuristics, vehicle routing, and network flow.
• Hands-on experience solving supply chain operations research problems such as warehouse routing, transportation optimization, inventory placement, network optimization, or procurement.
• Ability to take modelling problems from formulation and experimentation through production deployment and iteration.
• Strong engineering fluency across areas such as feature pipelines, solver integration, experimentation infrastructure, and model serving.
• Experience working with real-world operational data, including noisy, incomplete, or continuously changing datasets.
• Strong experimentation, backtesting, and model evaluation skills.
• Experience working with optimization solvers and production-grade data science workflows.
• Demonstrated experience applying AI/LLM tools to scientific workflows such as model formulation, problem decomposition, or experiment design.
• Strong written and verbal communication skills, with the ability to explain complex technical concepts to technical and non-technical stakeholders.
• Ability to work independently in ambiguous environments and collaborate effectively across teams and geographies.

Responsibilities

• Own meaningful modelling workstreams across dynamic warehouse routing, shipping cost optimization, multimodal transportation, inventory placement, network flow, and PO allocation.
• Take modelling problems end-to-end, from problem framing and data preparation through model development, deployment, and iteration.
• Translate complex operational challenges into well-defined optimization problems with clear objectives, constraints, and measurable success criteria.
• Apply operations research methodologies, including LP, MIP, CP, heuristics, vehicle routing, and network flow.
• Select, configure, and tune appropriate optimization solvers and methodologies based on problem characteristics.
• Design and run rigorous experiments using historical and operational data to evaluate model quality and business impact.
• Analyze model performance, identify limitations, and iterate on approaches based on scientific and operational evidence.
• Apply AI-native workflows, including LLM-assisted model formulation, agentic decomposition of complex optimization problems, and AI-augmented experiment design.
• Evaluate AI-generated approaches alongside classical optimization techniques using measurable outcomes and scientific rigor.
• Validate AI-generated hypotheses, recommendations, and modelling approaches before incorporating them into production decision-making.
• Contribute to team standards and best practices for applying AI effectively and responsibly within operations research.
• Build and deploy optimization models into production rather than limiting work to analytical prototypes.
• Own the monitoring, performance evaluation, and iteration lifecycle of models after deployment.
• Develop and maintain feature pipelines, optimization workflows, and model-serving components.
• Partner with Planning Tools Engineering on solver integration, feature stores, evaluation frameworks, and model-serving infrastructure.
• Ensure models remain performant, reliable, and maintainable as supply chain networks and operational conditions evolve.
• Apply engineering best practices around reproducibility, testing, monitoring, experimentation, and production model quality.
• Partner with the Palo Alto Planning Science team on shared supply chain optimization problems and modelling methodologies.
• Communicate modelling approaches, assumptions, results, limitations, and trade-offs through clear written documentation.
• Collaborate effectively across distributed teams and time zones with a strong emphasis on asynchronous communication.
• Work closely with logistics, warehouse, and supply chain planning stakeholders to understand operational challenges and business requirements.
• Translate operational realities into well-defined optimization problems and actionable modelling requirements.
• Convert model outputs into recommendations and decision-support capabilities that operations teams can effectively use.
• Clearly communicate the strengths, limitations, assumptions, and appropriate applications of scientific models.
• Influence technical and business roadmaps through data-driven insights and rigorous modelling.

Skills

Operations research

Data science

Optimization

Engineering fluency

Experimentation

Education

Advanced degree in operations research

Industrial engineering

Computer science

Statistics

Tools

Gurobi

CPLEX

OR-Tools

Job description

We are seeking a Senior Data Scientist - Supply Chain Operations Research to join our Supply Chain Planning Science team in Bangalore. In this role, you will develop and productionize advanced operations research and optimization solutions that influence critical supply chain decisions across warehouse routing, transportation, inventory planning, and network optimization.

You will own meaningful modelling workstreams end-to-end, from problem formulation and experimentation through production deployment, monitoring, and iteration. You will work closely with data science, planning tools engineering, and supply chain stakeholders across Bangalore and Palo Alto to translate complex operational challenges into scalable, measurable solutions.

This role is ideal for someone who combines strong operations research fundamentals with engineering fluency and a bias toward production impact. You will apply rigorous scientific methodology to real-world supply chain problems while helping the team adopt AI-native approaches to modelling, experimentation, and optimization.

The core responsibilities for the job include the following:

Operations Research and Modelling:

• Own meaningful modelling workstreams across dynamic warehouse routing, shipping cost optimization, multimodal transportation, inventory placement, network flow, and PO allocation.
• Take modelling problems end-to-end, from problem framing and data preparation through model development, deployment, and iteration.
• Translate complex operational challenges into well-defined optimization problems with clear objectives, constraints, and measurable success criteria.
• Apply operations research methodologies, including linear programming (LP), mixed-integer programming (MIP), constraint programming (CP), heuristics, vehicle routing, and network flow.
• Select, configure, and tune appropriate optimization solvers and methodologies based on problem characteristics.
• Design and run rigorous experiments using historical and operational data to evaluate model quality and business impact.
• Analyze model performance, identify limitations, and iterate on approaches based on scientific and operational evidence.

AI-Native Science:

• Apply AI-native workflows, including LLM-assisted model formulation, agentic decomposition of complex optimization problems, and AI-augmented experiment design.
• Evaluate AI-generated approaches alongside classical optimization techniques using measurable outcomes and scientific rigor.
• Validate AI-generated hypotheses, recommendations, and modelling approaches before incorporating them into production decision‑making.
• Contribute to team standards and best practices for applying AI effectively and responsibly within operations research.

Production and Engineering:

• Build and deploy optimization models into production rather than limiting work to analytical prototypes.
• Own the monitoring, performance evaluation, and iteration lifecycle of models after deployment.
• Develop and maintain feature pipelines, optimization workflows, and model‑serving components.
• Partner with Planning Tools Engineering on solver integration, feature stores, evaluation frameworks, and model‑serving infrastructure.
• Ensure models remain performant, reliable, and maintainable as supply chain networks and operational conditions evolve.
• Apply engineering best practices around reproducibility, testing, monitoring, experimentation, and production model quality.

Cross‑Geography Collaboration:

• Partner with the Palo Alto Planning Science team on shared supply chain optimization problems and modelling methodologies.
• Ensure solutions developed across Bangalore and Palo Alto integrate effectively and avoid duplicated efforts.
• Communicate modelling approaches, assumptions, results, limitations, and trade‑offs through clear written documentation.
• Collaborate effectively across distributed teams and time zones with a strong emphasis on asynchronous communication.

Business Partnership:

• Work closely with logistics, warehouse, and supply chain planning stakeholders to understand operational challenges and business requirements.
• Translate operational realities into well‑defined optimization problems and actionable modelling requirements.
• Convert model outputs into recommendations and decision‑support capabilities that operations teams can effectively use.
• Clearly communicate the strengths, limitations, assumptions, and appropriate applications of scientific models.
• Influence technical and business roadmaps through data‑driven insights and rigorous modelling.

Requirements:

• 5-8 years of experience in operations research, data science, applied mathematics, industrial engineering, or a related quantitative field.
• Demonstrated experience building and deploying production models that have delivered measurable business impact.
• Strong expertise in optimization methodologies, including LP, MIP, CP, heuristics, vehicle routing, and network flow.
• Hands‑on experience solving supply chain operations Research problems such as warehouse routing, transportation optimization, inventory placement, network optimization, or procurement.
• Ability to take modelling problems from formulation and experimentation through production deployment and iteration.
• Strong engineering fluency across areas such as feature pipelines, solver integration, experimentation infrastructure, and model serving.
• Experience working with real-world operational data, including noisy, incomplete, or continuously changing datasets.
• Strong experimentation, backtesting, and model evaluation skills.
• Experience working with optimization solvers and production‑grade data science workflows.
• Demonstrated experience applying AI/LLM tools to scientific workflows such as model formulation, problem decomposition, or experiment design.
• Strong written and verbal communication skills, with the ability to explain complex technical concepts to technical and non‑technical stakeholders.
• Ability to work independently in ambiguous environments and collaborate effectively across teams and geographies.

Preferred:

• Advanced degree in operations research, industrial engineering, computer science, statistics, applied mathematics, or a related quantitative field.
• Experience in e‑commerce, retail, logistics, supply chain, transportation, or warehouse optimization.
• Experience with optimization solvers such as Gurobi, CPLEX, OR‑Tools, or similar.
• Experience solving large‑scale vehicle routing, network optimization, or other combinatorial optimization problems.
• Experience building production‑grade optimization or decision‑support platforms.
• Experience working with distributed data science or operations research teams.
• Strong experience using AI/GenAI tools to accelerate scientific experimentation and modelling workflows.
• Experience with cloud‑based data science, optimization, and model deployment platforms.