Ml Engineer

Straive; Bengaluru; Hybrid; INR 1,500,000 - 3,000,000; Full time

Job summary

Straive in Bengaluru seeks ML engineers to design, build, and deploy production-grade pricing, demand forecasting, promotion‑effectiveness, and competitor‑pressure models for retail/CPG clients. The role turns data science prototypes into reliable, automated systems that drive revenue, margin, price competitiveness, and customer value.

You will work with data scientists to deploy models on transaction history, product hierarchies, prices, promotions, inventory and external factors.

Qualifications

• Proven Python and SQL coding skills.
• Hands-on data analysis with Pandas/NumPy and statistics.
• Experience with ML deployment, CI/CD, and experiment tracking.
• Strong knowledge of probability, hypothesis testing, and predictive modelling.

Responsibilities

• Design, build, and deploy production-grade ML models for pricing, demand forecasting, promotions, and competitor pressure.
• Turn data science prototypes into automated systems that drive revenue, margin, price competitiveness, and customer value.
• Collaborate with data scientists and engineers to monitor production models and report performance.

Skills

Python

SQL

Pandas

NumPy

Scikit-learn

MLOps

Model deployment

Docker

Airflow

BigQuery

Spark

Tools

Vertex AI

BigQuery ML

Job description

Role: ML engineer
Location: Bengaluru
Experience: 3-6 years
Cloud Platform: Preferably Google Cloud Platform, AWS and Azure will also work
Role Summary
Seeking ML engineers to design, build, and deploy production-grade pricing, demand-forecasting, promotion-effectiveness, and competitor-pressure models for retail/CPG clients. The role will turn data science prototypes into reliable, automated systems that deliver recommendations to improve revenue, margin, price competitiveness, promotional effectiveness, and customer value.
The ML engineer will work closely with data scientists to deploy and operate models built on transaction history, product hierarchies, prices, promotions, inventory, competitor prices, customer behaviour, seasonality, and external factors. Responsibilities include building training and inference pipelines, managing model versioning and retraining, and monitoring performance, drift and data quality in production

Mandatory Skills

• Strong Python and SQL skills.
• Proficiency in Pandas, NumPy, Scikit-learn, statistical modelling, and visualization.
• Experience with MLOps practices: model deployment (batch and real-time), CI/CD. Experiment tracking, model versioning and retraining automation (e.g., MLflow, Docker, Airflow)
• Strong foundation in probability, hypothesis testing, confidence intervals, regression, experimentation, and predictive modelling.
• Hands on experience productionizing models including scalable feature engineering pipelines, automated model validation and hyperparameter tuning.
• Understanding of ML models performance and latency trade-offs in production.
• Ability to collaborate with data scientists, engineers and commercial stakeholders, and to document and communicate model behaviour, performance and limitations clearly.
• Experience working with large datasets on BigQuery, Spark, or another cloud data platform.

Preferred Experience

• Prior experience building production models for retail/CPG domain.
• Hands on experience with Vertex AI (Pipelines, Model registry, endpoints), BigQuery ML, or GCP-based model-deployment and orchestration.
• Experience setting up model and data monitoring (performance, drift, data quality) and surfacing it through Power BI, Tableau, Looker or Grafana dashboards.
• Ability to translate pricing and commercial concepts (price elasticity, demand response, promotion uplift, and commercial performance metrics) into robust, reusable model features and evaluation frameworks.
• Knowledge of Logistic and Linear Regression, Random Forest, XGBoost, LightGBM, clustering, and ensemble methods.