Qualification | BTech Experience (in years) | 8 Job Description | Role Overview We are looking for an AI Data Scientist to design and pilot an AI-enabled solution that accelerates data-quality rule definition, SQL generation, validation, and assessment. The role will work closely with business, Data Office, data engineering, and platform teams to convert business context and metadata into reliable, explainable, human-approved data-quality controls. Key Responsibilities · Design and develop GenAI/LLM workflows that generate data-quality rules, business descriptions, and SQL from metadata, sample data, and business context. · Build prompt, retrieval, and evaluation approaches that improve output relevance, consistency, and repeatability. · Create human-in-the-loop review mechanisms for users to accept, modify, reject, and approve generated rules. · Partner with data engineers to adapt and execute approved SQL safely in authorized environments. · Define and run tests for rule quality, SQL validity, repeatability, coverage, and model limitations. · Support standardized assessment reporting, defect analysis, and integration with existing data-quality and workflow tools. · Document solution design, assumptions, guardrails, experiments, and production-readiness requirements. Required Experience & Skills · Hands-on experience in data science, machine learning, or applied Generative AI/LLM solutions. · Strong Python and SQL skills, with practical experience working with structured data and metadata. · Experience with prompt engineering, retrieval-augmented generation, embeddings, model evaluation, and API-based AI services. · Hands-on exposure to AWS-based enterprise data platforms, particularly Amazon Redshift, Glue, IAM, Data brew, and orchestration services; experience with dbt and automated data-quality testing is an advantage. · Understanding data-quality concepts such as completeness, validity, consistency, uniqueness, accuracy, and timeliness. · Ability to translate business requirements into testable technical solutions and communicate results to non-technical stakeholders. · Experience with Git, APIs, cloud/data platforms, and agile delivery practices. · Total 7-8 YOE Preferred · Experience with enterprise data governance, metadata catalogues, data observability, or DQ platforms. · Exposure to secure AI deployment, access controls, monitoring, and responsible AI practices. · Experience productionizing prototypes or building lightweight user interfaces for AI-assisted workflows. Skill Set Required | Hands-on experience in data science, machine learning, or applied Generative AI/LLM solutions. · Strong Python and SQL skills, with practical experience working with structured data and metadata. · Experience with prompt engineering, retrieval-augmented generation, embeddings, model evaluation, and API-based AI services. · Hands-on exposure to AWS-based enterprise data platforms, particularly Amazon Redshift, Glue, IAM, Data brew, and orchestration services; experience with dbt and automated data-quality testing is an advantage. · Understanding data-quality concepts such as completeness, validity, consistency, uniqueness, accuracy, and timeliness. · Ability to translate business requirements into testable technical solutions and communicate results to non-technical stakeholders. · Experience with Git, APIs, cloud/data platforms, and agile delivery practices. · Total 7-8 YOE
