Blend is a premier AI services provider, committed to co-creating meaningful impact for its clients through the power of data science, AI, technology, and people. We help organisations solve complex business challenges by combining deep domain understanding with modern data and AI capabilities. Our teams work across strategy, analytics, engineering, and product delivery to create scalable, high-value solutions that improve decision-making, efficiency, and growth.
Job Description
We are looking for an experienced Senior Data Engineer to support the delivery of an AI-powered conversational analytics capability for a large enterprise client. This role will be critical in preparing complex business data for AI consumption, developing semantic layers, and ensuring data is structured for accurate, efficient, and governed querying by LLM-driven workflows. The ideal candidate will have strong hands-on experience in modern cloud data engineering, data modelling, semantic design, and building scalable pipelines for analytical and AI use cases. This person will work closely with AI Engineers, Software Engineers, Data Scientists, and DevOps teams to ensure the data foundation supports natural language querying, narrative insight generation, anomaly detection, and future scalability.
Responsibilities
- Design, build, and maintain scalable data pipelines to prepare complex business data for conversational analytics use cases.
- Develop and maintain semantic layers, business logic mappings, and data structures that improve AI understanding of client taxonomies, KPIs, hierarchies, and business concepts.
- Model and transform complex business data into structures optimised for query generation, interpretation, and insight production.
- Partner with AI and software engineering teams to support LLM workflows, agent orchestration, and governed access patterns.
- Implement robust ingestion, transformation, and data quality processes for structured analytical datasets.
- Support live-query and cached data access patterns depending on agreed architecture and performance needs.
- Ensure data is accessible, explainable, and aligned to business definitions used in evaluation and user acceptance testing.
- Collaborate with Data Scientists to support ground-truth evaluation, validation datasets, and regression testing.
- Work with architects and client data stakeholders to align designs with enterprise data standards, governance requirements, and long-term maintainability.
- Contribute to production readiness through documentation, testing, monitoring, and knowledge transfer to internal teams.
- Support deployment of data solutions into controlled Dev, Test, and Production environments.
- Help shape scalable patterns for future expansion into additional datasets and more advanced analytical capabilities.
Qualifications
- 6+ years of experience in Data Engineering, ideally in cloud-based analytical environments.
- Strong hands-on experience with SQL and Python for data processing and transformation.
- Experience building scalable data pipelines and transformation workflows for large, complex datasets.
- Strong understanding of data modelling, semantic layer design, and analytical data structures.
- Experience with cloud data platforms such as BigQuery, Databricks, Snowflake, or similar.
- Experience working with large analytical, transactional, or domain-rich enterprise datasets is highly desirable.
- Understanding of governed data access, role-based permissions, and enterprise data standards.
- Experience supporting AI, ML, or LLM use cases through data preparation, metadata design, or retrieval and query optimisation.
- Familiarity with testing, validation, and monitoring for data quality and reliability.
- Experience with Git-based development workflows.
- Strong communication skills and ability to work collaboratively with technical and business stakeholders.
Good to Have
- Experience with GCP services such as BigQuery, Pub/Sub, Cloud Run, or Vertex AI.
- Familiarity with semantic modelling for NLP, conversational analytics, or AI-driven querying.
- Understanding of prompt-aware data design or retrieval-augmented architectures.
- Experience working in regulated enterprise environments with strong governance requirements.
- Exposure to CI/CD, infrastructure-as-code, and production deployment practices.
- Experience contributing to knowledge transfer and internal capability enablement.
