Job Summary
Key Responsibilities
2. Provide technical leadership and guidance to the development team throughout the project lifecycle.
3. Collaborate with stakeholders to gather requirements, define project scope, and establish technical solutions that meet business needs.
4. Conduct code reviews, ensure coding standards are followed, and troubleshoot technical issues as needed.
5. Manage project timelines, resource allocation, and deliverables to ensure successful project completion.
6. Stay updated on industry trends and best practices related to .net, angular, and sql server technologies.
Skill Requirements
2. Strong experience in angular framework for frontend development.
3. Solid understanding of sql server and database management.
4. Excellent problem-solving skills and ability to think critically.
5. Demonstrate leadership abilities
6. Effective communication skills and ability to collaborate with cross functional teams.
Other Requirements
Key Responsibilities
- Build and maintain pipelines feeding structured/unstructured data into RAG retrieval layers
- Design and optimise SQL data models; tune indexing and query performance
- Process semi-structured content (JSON, XML, extraction outputs) for downstream LLM use
- Build chunking/embedding pipelines; manage vector store indexing and metadata hygiene
- Apply Responsible AI data practices – mask PII/PHI before data reaches an LLM API
- Deploy and monitor pipelines on Azure with CI/CD hygiene
Must-Have Skills
- 6–8 yrs data engineering with strong SQL and ETL/ELT experience
- Hands-on with a vector store (ChromaDB, Pinecone, or pgvector)
- Proficiency processing JSON/XML at scale; working Python skills
- Azure basics – containerised deployment, CI/CD, log analysis
- Understanding of PII/PHI handling and data compliance
Good to Have
- RAG pipeline design experience (chunking, embedding, retrieval tradeoffs)
- Exposure to LLM API integration and AI observability
Non-Technical Competencies
- AI-native mindset – understands LLM limits and failure modes
- Ambiguity tolerance – delivers against incomplete or evolving requirements
- Communication clarity – explains technical decisions to both engineers and business stakeholders
- Responsible AI awareness – flags PII/PHI exposure and knows when output needs human review