• Architect and own the enterprise AI data platform — the unified, governed layer that ingests, transforms, stores, and serves all data consumed by AI systems across the organisation. • Design multi-domain data models (lakehouse, data mesh, event-driven) that are structured from day one to serve AI workloads: clean lineage, versioned schemas, well-documented contracts, and low-latency serving APIs. • Own the full data stack: real-time streaming (Kafka, Spark Structured Streaming), batch processing (Databricks, PySpark, Delta Lake), cloud storage and compute (AWS, Azure), and data quality /metadata management. • Ensure this platform is the single, authoritative data source for all downstream consumers — conversational AI, dashboard assistants, autonomous agents, ML models, and reporting — eliminating data silos and conflicting truths. • Drive modernisation of legacy pipelines (on-prem ETL, batch DWH) to cloud-native, AI-ready architectures with measurable improvements in cost, latency, and delivery velocity. • Design the semantic layer that sits above raw data — business-aligned ontologies, entity relationships, domain taxonomies, and knowledge graphs — so AI systems understand context, not just tokens. • Build and maintain knowledge graphs (Neo4j or equivalent) that capture relationships between business entities, policies, KPIs, hierarchies, and domain rules — enabling structured reasoning alongside unstructured retrieval. • Define and govern a feature store and semantic data contracts that serve both classical ML models and LLM-based applications from a single, well-versioned, trusted source. • Own metadata management, data lineage, and audit trails across the semantic layer — ensuring every AI system can trace its outputs back to source data with full accountability. • Design and enforce a comprehensive data governance model that governs access for both human users and AI agents — with role-based access control (RBAC), attribute-based policies, and agent-specific permission scopes that prevent privilege escalation.

• Build, test, and maintain production pipelines (batch & real-time) on Snowflake, PySpark, Delta Lake, and Kafka. • Implement data quality checks, schema validation, and alerting at every pipeline stage. • Migrate legacy ETL/DWH to cloud-native AWS/Azure architectures with measurable latency and cost improvements. • Maintain CI/CD pipelines: automated testing, deployment, rollback, and IaC (Terraform, GitHub Actions). • Build end-to-end retrieval infrastructure: document ingestion, embedding pipelines, vector store management (Pinecone, FAISS, ChromaDB, OpenSearch), and hybrid retrieval layers. • Implement chunking, metadata filtering, and re ranking — tuning for precision, recall, and latency. • Maintain data freshness and index consistency; instrument with context relevance and faithfulness metrics. • Implement and maintain business entity mappings, ontologies, and knowledge graphs (Neo4j) per Architect design. • Build and version the feature store and semantic data contracts serving both ML models and LLM applications. • Manage metadata, data lineage, and audit trail instrumentation across the platform. • Build ML data infrastructure: training curation, feature engineering, MLflow experiment tracking, dataset versioning. • Support LLM fine-tuning workflows — corpus curation, quality filtering, dataset formatting. • Implement automated evaluation pipelines: factual accuracy, hallucination detection, regression tracking. • Maintain production monitoring dashboards for pipeline health, model metrics, and alerting. • Build and maintain data APIs, tool schemas, and memory/state stores that autonomous agents depend on. • Implement agent observability: capture inputs, retrieved context, tool calls, reasoning traces, and outputs. • Maintain text-to-SQL layers, semantic query interfaces, and context APIs for conversational AI consumers. • Implement RBAC, attribute-based access, PII detection/masking, data classification, and audit logging. • Enforce data contracts and schema governance with automated breaking-change detection and versioned migrations. • Build data quality monitoring (completeness, freshness, consistency) with automated alerting and root-cause tooling. • Support compliance readiness: audit trails, data provenance, and regulatory documentation.

• Design, develop, and maintain scalable data pipelines and integration solutions within the Azure ecosystem • Build and support enterprise data platforms that consolidate information from multiple source systems • Develop ETL/ELT processes to ingest, transform, validate, and distribute business-critical data • Contribute to data modelling, data quality, and governance initiatives • Support Master Data Management (MDM) processes and ensure consistency across systems • Work with structured and semi-structured data from ERP, business applications, APIs, databases, and external sources • Collaborate with business and technical stakeholders to translate requirements into scalable data solutions • Participate in deployment, testing, monitoring, and continuous improvement activities • Contribute to CI/CD pipelines, automation, and DevOps best practices • Actively participate in Agile ceremonies and team collaboration

• Build and maintain scalable data pipelines, transformations, and reporting models using dbt, SQL, Python, and Snowflake. • Develop and optimize data ingestion workflows, API integrations, and CDC pipelines using established engineering frameworks and best practices. • Implement data quality checks, testing, monitoring, and observability mechanisms to ensure reliable and trustworthy data products. • Design and maintain analytics-ready data models, including reporting marts and dimensional models that support business insights. • Leverage AI-powered development tools such as GitHub Copilot and Claude to improve productivity, code quality, and documentation. • Collaborate with analysts, BI teams, and stakeholders to define metrics, clarify business logic, and deliver impactful data solutions. • Contribute to data governance, compliance, and platform reliability by following data contracts, security standards, and engineering best practices.