Senior Data Engineer (Agentic Workflows & Data Platforms)
Smartsourcing View all jobs
- Cebu City, Cebu
- Permanent
- Full-time
- Agentic Workflow Development
- Architect and deploy multi-agent systems (using frameworks like LangGraph) to automate data pipeline design, data profiling, and semantic validation
- Integrate LLMs and agentic tools such as Claude Code Skills and Agent Teams into CI/CD and data engineering workflows
- Framework Engineering
- Build and maintain highly opinionated, deterministic engineering templates that standardize data ingestion
- Output declarative specification files rather than raw, unpredictable AI-generated code
- Develop robust boilerplates and reusable, configuration-driven pipeline patterns to replace bespoke free-form Spark code
- Deterministic Quality Gates
- Implement strict, non-LLM validation loops (e.g., Python scripts checking for known code smells) to ensure AI-generated logic meets rigorous production standards before execution
- Maintain and evolve validation frameworks as patterns change
- Architecture Evolution
- Drive data architecture evolution using local/cloud LLMs and agentic personas to accelerate ETL/ELT workflows
- Manage current Medallion/Kimball models while preparing infrastructure for transition toward loosely connected, decentralized data ontologies
- Design fault-tolerant and self-healing pipelines
- Data Management & Modeling
- Understand and continuously improve the business concepts behind database design, source systems, and data models used for reporting
- Business Collaboration & Leadership
- Work directly with seniors, team leaders, and managers to identify shortcomings in ETL and database technology and devise solutions
- Mentor non-senior team members and support team leaders in supervising overall performance
- Systems Auditing & Security
- Conduct routine audits of data storage systems and databases to ensure security, accuracy, and efficiency
- Apply secure data engineering best practices in line with ISO 27001:2022
- Bachelor's degree in Computer Science, Data Engineering, Information Management, or equivalent work experience
- 5+ years of Data Engineering experience with deep expertise in Databricks/Microsoft Fabric and Delta Lake
- Hands-on experience integrating LLMs and agentic frameworks into CI/CD and data engineering workflows
- Strong understanding of dimensional modeling, Medallion architectures, and modern metadata management
- High proficiency in Python and SQL
- Experience applying software engineering best practices (test coverage, DRY principles, robust templating) to AI-augmented development
- Strong critical thinker with a bias toward engineering rigor over hype
- Confident communicator who can articulate technical trade-offs to non-technical stakeholders
- Collaborative team player with a genuine interest in mentoring junior engineers
- Microsoft Fabric, Databricks, Delta Lake, and Azure Data Factory
- Agentic AI frameworks such as Claude Code Skills, BMAD, or similar
- Python for pipeline development, framework engineering, and automation
- SQL — database design, stored procedures, functions, views
- Data modeling: Kimball dimensional modeling and Medallion architecture
- Data warehousing and Lakehouse patterns
- CI/CD pipelines with integrated AI/LLM validation gates
- Experience with Power BI or a similar BI/visualization tool
- 5-day Christmas Leave (unwrap real time off)
- Healthcare from Day 1 for you and your family (because healthcare matters)
- Free lunch and barista-crafted coffee daily (we take our caffeine seriously)
- Night shift differential for evening schedules
- Subsidized gym membership and sports wellness clubs including hiking and free-diving
- Smartsourcing Exclusives (deals made just for you)
- Themed BFFs, monthly knockoffs, summer parties
- Community give-back programs and personal development workshops
- And so much more!