Project Role : Data Platform Engineer
Project Role Description : Assists with the data platform blueprint and design, encompassing the relevant data platform components. Collaborates with the Integration Architects and Data Architects to ensure cohesive integration between systems and data models.
Must have skills : Data Engineering
Good to have skills : NA
Minimum 5 Year(s) Of Experience Is Required
Educational Qualification : 15 years full time education
Summary:
Design and build enterprise knowledge foundations that enable accurate, governed, and context-aware AI and agentic systems.
Advanced proficiency with Databricks Assistant, GitHub Copilot or Cursor, alongside LlamaIndex, LangChain, Neo4j, Pinecone, Weaviate, Elasticsearch/OpenSearch and cloud vector-search services, to accelerate governed ingestion, knowledge-graph and production RAG engineering.
Must have built and operated production data, search, knowledge, or retrieval platforms. Experience limited to basic vector-database prototypes is insufficient.
Roles & Responsibilities:
- Architect ingestion, transformation, indexing, retrieval, and knowledge-enrichment pipelines.
- Build production RAG systems using structured, unstructured, graph, and metadata-driven retrieval.
- Define document parsing, chunking, taxonomy, ontology, entity resolution, and lineage strategies.
- Implement access-aware retrieval, freshness controls, quality checks, and auditability.
- Optimize retrieval quality, latency, scale, and cost.
- Partner with AI engineers on context construction and grounding.
- Mentor engineers and define reusable knowledge-engineering standards.
Professional & Technical Skills:
- Python, SQL, distributed processing, and orchestration.
- Vector search, hybrid retrieval, knowledge graphs, metadata, and semantic modeling.
- Document pipelines, search, data quality, lineage, and access control.
- Cloud, APIs, CI/CD, observability, and performance engineering.
