Data Scientist – Job Description

Location: Bangalore, India
Experience: 5–6 Years
Employment Type: Full-time

We are looking for a Data Scientist with 5–6 years of experience who can work closely with our engineering and product teams to build data-driven intelligence capabilities for the platform.

Key Responsibilities

Data Science & Machine Learning

- Analyze large and complex datasets to identify patterns, trends, anomalies, and business opportunities.
- Develop statistical and machine-learning models for business and procurement use cases.
- Perform feature engineering, model selection, training, evaluation, and optimization.
- Develop models for forecasting, classification, clustering, anomaly detection, segmentation, and recommendation where applicable.
- Define appropriate evaluation metrics and validate model performance.
- Translate business problems into measurable data-science problems.

Procurement & Business Intelligence

Work on use cases such as:

- Spend analysis and classification
- Supplier performance and risk analysis
- Supplier segmentation
- Demand and inventory forecasting
- Price and cost analysis
- Procurement opportunity identification
- Anomaly and outlier detection
- Product/SKU-level analytics
- Channel and profitability analytics
- Business trend and market intelligence
- What-if and scenario analysis

Generative AI / LLM

- Develop and integrate AI/LLM-powered capabilities
- Work with RAG (Retrieval-Augmented Generation) architectures.
- Develop embedding and semantic-search pipelines.
- Work with vector databases such as Pinecone, FAISS, or equivalent technologies.
- Experiment with LLMs and prompt engineering for enterprise use cases.




- Build AI workflows that combine LLMs with structured business data and application APIs.
- Evaluate the accuracy, relevance, and reliability of AI-generated results.
- Help establish approaches for reducing hallucinations and improving response quality.

Data Engineering & Productionization

- Work closely with Data Engineers and Backend Engineers to build production-ready data pipelines.
- Work with structured and semi-structured data formats such as CSV, JSON and Parquet.
- Contribute to scalable ETL/ELT pipelines for datasets ranging from thousands to millions of records.
- Implement data validation, quality checks, transformations, and feature pipelines.
- Ensure models and analytical logic can be reproduced and deployed reliably.
- Collaborate on model deployment and monitoring in production environments.

Collaboration

- Work closely with Product, Engineering, Data Engineering, and AI teams.
- Understand business requirements and convert them into technical/data-science solutions.
- Communicate analytical findings clearly to both technical and non-technical stakeholders.
- Participate in architecture and technical design discussions.
- Document models, assumptions, experiments, datasets, and results.

Required Skills

Core Data Science

- 5–6 years of hands-on experience in Data Science / Machine Learning.
- Strong Python programming skills.
- Strong understanding of statistics and probability.
- Experience with:

- Pandas




- NumPy
- Scikit-learn
- Matplotlib / Seaborn or equivalent visualization tools

Robust understanding of supervised and unsupervised machine learning. Experience with model evaluation, feature engineering, and experimentation.

Machine Learning

Strong understanding of several of the following:

- Regression
- Classification
- Clustering
- Time-series forecasting
- Anomaly detection
- Recommendation systems
- NLP
- Dimensionality reduction
- Feature selection

Generative AI

Hands-on experience with:

- LLMs
- RAG
- Embeddings
- Vector databases
- Prompt engineering
- LangChain / LangGraph or equivalent frameworks
- OpenAI API or other LLM APIs

Data

- Strong SQL skills.
- Experience working with large datasets.
- Understanding of data modeling and data quality.
- Experience with ETL/ELT concepts.
- Experience with cloud data platforms is desirable.
- Experience with Parquet, DuckDB, Spark, or similar technologies is a plus.

Engineering

- Good understanding of REST APIs and service integration.
- Familiarity with Git and modern software development practices.
- Experience working with Docker and cloud environments is desirable.
- Exposure to CI/CD and MLOps practices is a plus.

Good to Have

Experience in one or more of the following areas would be highly valuable:

- Procurement analytics
- Supply chain analytics
- Retail analytics
- Inventory optimization
- Demand forecasting
- Spend analytics
- Supplier analytics
- SAP / SAP Ariba data
- Enterprise SaaS products
- Business intelligence platforms

Education

- Bachelor's or Master's degree in Computer Science, Data Science, Statistics, Mathematics, Engineering, or a related field.

📌 Data Scientist (Bengaluru)
🏢 S2V Automation
📍 Bengaluru