AI Data Solutions Engineer

Binariks is looking for a highly motivated AI Data Solutions Engineer to bridge the gap between complex business challenges and production-ready AI. Working embedded directly within our clients' teams, you will turn ambiguous, messy business domains into clean, well-modeled, and governed data ecosystems — and then build intelligent LLM/RAG solutions directly on top of that foundation.

What We’re Looking For

• 5+ years of hands-on experience in Data Engineering, Analytics Engineering, or Solutions Engineering.

• Practical experience building production-ready LLM applications in Python, including RAG pipelines, AI agents, embeddings, prompt engineering, and model evaluation.

• Strong command of data modeling across conceptual, logical, and physical layers.

• Deep familiarity with entity-relationship, dimensional, and canonical modeling, with the ability to translate complex business concepts into scalable data structures.

• Experience with metadata management and data catalogs (e.g., DataHub, Collibra, Alation, Unity Catalog, Dataplex, or AWS Glue), including building business glossaries and tracking data lineage.

• Hands-on experience with data quality profiling, rule definition, and monitoring using tools like dbt tests, Great Expectations, or Soda, alongside a solid understanding of Master Data Management (MDM) principles.

• Advanced SQL proficiency and practical experience with at least one major cloud platform (AWS, GCP, or Azure), preferably Azure.

• Strong facilitation skills: ability to run discovery workshops with business stakeholders, map domain language into technical models, and clearly explain architectural trade-offs to non-technical audiences.

• Proven track record in client-facing roles, working embedded within customer teams and navigating ambiguous environments.

• Upper-Intermediate / Advanced English (B2+ / C1).

Will be a plus

• Ontology work: OWL, RDF, SKOS, SHACL, Protégé

• Knowledge graphs such as Neo4j, Neptune, Stardog or GraphDB, using SPARQL or Cypher

• GraphRAG or other ways of feeding semantic context to LLMs

• Semantic layer tools such as dbt Semantic Layer, Cube or AtScale

• Domain standards such as FHIR (healthcare) or ACORD (insurance)

Your responsibilities

• Design, build, and deploy production-grade LLM solutions in Python, including RAG pipelines, intelligent agents, and embedding workflows.

• Establish prompt engineering best practices and robust evaluation frameworks to ensure accuracy, reliability, and relevance of AI outputs.

• Architect conceptual, logical, and physical data models (ER, dimensional, and canonical) that serve as a clean, scalable foundation for both analytics and AI applications.

• Implement and maintain data catalogs, business glossaries, and end-to-end data lineage using modern metadata management platforms (such as DataHub, Unity Catalog, Collibra, or AWS Glue).

• Define data profiling standards, automated quality checks, and monitoring pipelines (using dbt tests, Great Expectations, or Soda) while supporting Master Data Management (MDM) initiatives.

• Write performant SQL and build scalable data workflows within cloud ecosystems (AWS or Azure) to seamlessly connect enterprise data sources with downstream AI/analytics consumers.

• Work embedded within client teams to lead technical discovery workshops, uncover business needs, and translate complex domain concepts into structured data models and AI architectures.

• Navigate ambiguous environments, advising stakeholders on architectural trade-offs and technical feasibility in clear, business-friendly terms.