Senior Data Scientist — Supply Chain Forecasting & Demand Sensing

TecQubes Technologies; Bengaluru; Hybrid; INR 4,000,000 - 7,000,000; Full time

Job summary

TecQubes Technologies in Bengaluru (Bangalore), India, is seeking a Senior Data Scientist to own demand forecasting and demand sensing end to end. The role blends traditional time-series methods with modern AI/ML engineering to translate forecasts into actionable business decisions.

Hybrid work arrangement and a strong emphasis on end-to-end lifecycle ownership are expected. You will scope problems, engineer features, build validate and ship models to production, and collaborate with

Qualifications

• 5+ years applied DS delivering models used in production.
• Depth in time-series forecasting and demand sensing.
• Feature engineering & multivariate/causal modelling with point-in-time correctness.
• Command of the DS lifecycle as a repeatable framework.
• Supply chain or demand-planning domain experience.
• Strong Python & SQL; solid software engineering habits.
• Experience with MLOps, monitoring, explainability and GenAI/LLM.
• Ability to translate business needs into modeling and actionable insights.

Responsibilities

• Own time-series demand forecasting across products, locations and horizons.
• Develop demand sensing models using near real-time signals.
• Engineer features and multivariate/causal models.
• Maintain forecasting toolkit: ARIMA/ETS, LightGBM/XGBoost, DL methods.
• Own end-to-end DS lifecycle: framing, EDA, validation, deployment, monitoring.
• Translate forecasts into inventory, replenishment, and capacity actions.
• Integrate data contracts with planning systems; apply GenAI where valuable.

Skills

Time-series forecasting

Python

SQL

MLOps

Model deployment

SHAP explainability

Demand forecasting

Stakeholder communication

Data science lifecycle

Supply chain domain

Tools

LightGBM

XGBoost

ARIMA

ETS

SHAP

Job description

Role: Senior Data Scientist — Supply Chain Forecasting & Demand Sensing

Experience: 5+ years

Location: Bangalore, India (Hybrid)

We are sseeking a Senior Data Scientist to own demand forecasting and demand sensing end to end and turn forecasts into decisions the business acts on — working at the intersection of me-series forecasting, modern AI/ML engineering, and decision opmization. It is a hands‑on role owning the full data science lifecycle: you scope the problem, engineer the features, build and validate the models, and ship them to production.

What You'll Own

• Time‑series demand forecasting across products, locations, and horizons — capturing price, promotions, calendar/events, seasonality, weather effects etc.
• Demand sensing — short‑horizon models fusing near‑real‑me signals (POS/sell-through, orders, shipments, inventory, weather, market signals) to catch near‑term shifts and blend with the baseline forecast.
• Feature engineering & multi variate modelling — leakage‑free feature pipelines and multi variate/causal models capturing driver interactions, and cannibalization/halo effects.
• The forecasting toolkit — statistical (ARIMA/ETS), ML (LightGBM/XGBoost), and deep‑learning or probabilistic methods — choosing the right method for the problem, not the newest.
• The end‑to‑end DS lifecycle — framing, EDA, feature engineering, validation, deployment, monitoring, and explainability (SHAP), as a reproducible framework.
• Decisions & integration — translate forecasts into inventory, replenishment, fulfilment, and capacity actions; own the data contracts into the planning systems; and bring modern AI (LLMs/RAG/agents) to bear where it genuinely adds value.

Qualifications

• 5+ years applied DS delivering models used in production.
• Depth in me-series forecasting (ideally demand sensing) — evaluation, backtesting, failure modes.
• Feature engineering & multi variate/causal modelling with point‑in‑me correctness.
• Command of the DS lifecycle as a repeatable framework, not one-off notebooks.
• Supply chain / demand‑planning domain (retail, manufacturing, or logis cs).
• Strong Python & SQL; solid software‑engineering habits.
• Current AI/ML engineering — MLOps, monitoring, explainability, GenAI/LLM landscape.
• Businessmodeling translation and strong stakeholder communication.