Data Engineer

Data Knowledge Engineer / Data Engineer

Specialization: Knowledge Graphs, Data Engineering & Generative AI

Location: Bhat, Ahmedabad

Experience: 6+ Years

Duration: 6 Months (Extension Possible)

Salary: ₹90,000 – ₹1,20,000/month

Working Hours: 1:00 PM – 10:00 PM IST

Job Overview

We are looking for an experienced Data Knowledge Engineer / Data Engineer with strong expertise in knowledge graphs, ontology design, AWS data services, vector search, and LLM applications.

The ideal candidate will be responsible for building AI-ready data and knowledge platforms that support reliable retrieval and agentic workflows.

Key Responsibilities

• Design ontologies and knowledge representations using RDF, OWL, SKOS, and taxonomy modeling.
• Build graph solutions using Amazon Neptune or Neo4j for entities, dependencies, rules, and lineage.
• Implement OpenSearch/vector search and RAG, including graph-augmented generation and subgraph retrieval.
• Develop LLM applications using Amazon Bedrock, prompt engineering, and Strands Agents.
• Build Python/TypeScript AI pipelines using LangChain, LlamaIndex, or equivalent frameworks.
• Implement Text2SQL and agent-ready chunking, embedding, vector-store loading, and metadata pipelines.
• Work with Glue Catalog, S3 Tables, Athena, Redshift, Apache Iceberg, and Parquet.

Mandatory Requirements

6+ years of relevant Data Engineering / Knowledge Engineering experience.

• Strong Python, SQL, and data engineering skills.
• Expertise in ontology design, RDF, OWL, SKOS, taxonomy modeling, and knowledge representation.
• Strong graph database skills with Amazon Neptune or Neo4j.
• Experience with vector databases, RAG patterns, Amazon Bedrock, and LLM application development.
• Knowledge of AWS data stack, data quality, lineage, and schema-drift controls.

Good to Have

Enterprise ingestion via APIs, flat files, SFTP, CDC, batch, and incremental loads.

• Experience with Airflow, Glue, or Step Functions, including retries, backfills, and idempotent reruns.
• dbt or equivalent and Great Expectations or similar data-quality tooling.
• Familiarity with Databricks and TTL/Turtle files.

Engagement Details

This is a 6-month engagement with the possibility of extension.

Final compensation will depend on the candidate's relevant experience, technical skills, and interview performance.

Recruitment Note

We are looking for suitable resources who are currently working remotely/from home and may be able to manage a parallel engagement without affecting their existing responsibilities or delivery commitments.

Candidates working in a different time zone may be particularly suitable for this schedule.

Any parallel engagement must comply with the candidate's:

• Existing employment contract
• Confidentiality obligations
• Conflict-of-interest requirements
• Applicable working-hour rules
• Employer/client policies

Please submit only candidates who can reliably manage the required 1:00 PM – 10:00 PM IST working hours and deliver without conflicts.

Apply Now

Share your updated CV/resume for consideration.

Phone: 9327071692

Email: talent.execura@gmail.com