Senior Semantic Engineer - Knowledge Graphs (Hybrid, Islamabad)

PakistanPakistan·Islamabad
Other
2 views0 saves0 applied

Quick Summary

Key Responsibilities

Define and continuously improve the engineering approach across discovery, domain analysis, semantic modeling, implementation, data integration, testing, documentation, deployment, and operations.

Requirements Summary

A degree in Computer Science, Information Science, Data Engineering, or a related field is preferred. 8–10+ years of experience in software engineering, data engineering, or semantic engineering,

Technical Tools
Other

Requirements

~3 min read
  • A degree in Computer Science, Information Science, Data Engineering, or a related field is preferred. 
  • 8–10+ years of experience in software engineering, data engineering, or semantic engineering, with a proven track record of leading complex technical initiatives.
  • Strong engineering expertise, technical judgment, and demonstrated impact are prioritized over years of experience alone.
  • Strong foundations in software and data engineering, including the ability to design, build, test, secure, deploy, and operate reliable data-intensive systems.
  • Sound technical judgment across architecture, API design, data modeling, distributed systems, debugging, and engineering trade-offs.
  • Strong understanding of data semantics, including business concepts, entities, relationships, identifiers, definitions, and context, with the ability to represent them consistently across systems.
  • Practical experience designing production-grade knowledge graphs, ontologies, taxonomies, semantic layers, canonical data models, or equivalent knowledge representation approaches.
  • Familiarity with semantic technologies and tools, including RDF, OWL, SKOS, SPARQL, SHACL, Protégé, TopBraid, and PoolParty, as well as graph databases and triple stores such as Neo4j, Amazon Neptune, GraphDB, and Stardog.
  • Experience with data integration, transformation, synchronization, entity resolution, record linkage, master data management (MDM), product information management (PIM), or data reconciliation across enterprise systems.
  • Proficiency in Python and at least one other suitable programming language, with experience developing data pipelines, APIs, services, and automated tests.
  • Familiarity with relational databases, search platforms, and other data storage technologies.
  • Experience working with CPG, retail, manufacturing, product master data, supply chain, commercial, retailer, or syndicated market data.
  • Familiarity with GS1 standards, including GTIN, GPC, GDSN, GS1 Web Vocabulary, or schema.org Product.
  • Experience integrating SAP S/4HANA or MDG with PIM/MDM platforms such as Salsify, Syndigo, Stibo, or Informatica.
  • Experience with GraphRAG, hybrid retrieval, semantic search, vector search, LLM applications, or AI-agent integration, where these approaches address specific product requirements.
  • Experience with Azure data services, including Azure Data Factory, Azure Databricks, Microsoft Fabric, Synapse, Azure AI Search, Azure OpenAI, Azure DevOps, or Azure Kubernetes Service.
  • Familiarity with event-driven architectures, streaming ingestion, change data capture, and data platform monitoring.
  • Experience with NLP or AI-assisted extraction of product attributes and business knowledge from specifications, labels, and enterprise documents.
  • Demonstrated ability to use AI coding tools and agents effectively in real engineering environments, understanding their strengths, limitations, and failure modes.
  • Experience improving engineering delivery capacity through automation, reusable systems, tooling, or AI-agent-enabled workflows.
  • Strong understanding of data quality, governance, lineage, provenance, model lifecycle management, enterprise data security, threat modeling, and secure-by-design architecture.
  • Strong communication and collaboration skills, with the ability to work effectively across Product, Business, Data, AI, and Engineering teams.
  • Ability to translate ambiguous business requirements into practical engineering solutions and communicate technical decisions clearly.
  • Experience leading or contributing to teams that have increased engineering delivery capacity through AI coding agents, automation, or redesigned engineering workflows.

Responsibilities

~5 min read
  • →Define and continuously improve the engineering approach across discovery, domain analysis, semantic modeling, implementation, data integration, testing, documentation, deployment, and operations.
  • →Establish the technical vision, architecture direction, and engineering standards for enterprise semantic models, knowledge platforms, graph services, and data integrations.
  • →Provide hands-on technical leadership through architecture and model reviews, design discussions, code reviews, and complex problem resolution.
  • →Establish standards for using AI coding agents and tools across ontology development, schema mapping, data profiling, transformation development, testing, and documentation.
  • →Integrate AI-assisted workflows into engineering processes to improve development efficiency, consistency, and delivery capacity.
  • →Design workflows that enable engineers to delegate well-defined tasks to AI agents while maintaining human oversight of business meaning, model integrity, data quality, security, and production changes.
  • →Identify appropriate use cases for AI agents, validate their outputs, and ensure human judgment is applied where necessary.
  • →Increase engineering delivery capacity through automation, reusable semantic assets, shared tooling, improved domain context, and agent-enabled workflows rather than relying solely on additional headcount.
  • →Design and evolve semantic models for CPG and commercial domains, including products, brands, categories, packaging, suppliers, retailers, customers, pricing, promotions, RGM/TPM, and retail execution.
  • → Define canonical business entities, relationships, identifiers, vocabularies, and semantic contracts to ensure consistency across enterprise applications.
  • →Design knowledge graph and semantic data architectures connecting product, customer, retailer, supply chain, pricing, promotion, RGM/TPM, and retail execution domains.
  • →Select appropriate representations and technologies, including RDF, OWL, SKOS, property graphs, relational models, and search indexes, based on business needs, interoperability, operational constraints, and cost.
  • →Integrate and harmonize data from SAP/ERP, PLM, PIM, MDM, syndicated market data, retailer POS, e-commerce feeds, and enterprise documents.
  • →Develop reliable entity-resolution and master data reconciliation capabilities to identify, match, and deduplicate products, customers, suppliers, and retailers across inconsistent identifiers and naming conventions.
  • →Build semantic interfaces, APIs, and MCP-compatible knowledge access services where appropriate, enabling enterprise applications and AI agents to securely access business entities, context, and relationships.
  • →Support business use cases including analytics, search, recommendations, digital shelf, product traceability, ingredient and allergen traceability, labeling compliance, and packaging/ESG reporting.
  • →Make enterprise knowledge accessible to AI-enabled applications and agents through governed, reliable interfaces.
  • →Evaluate semantic search, vector search, knowledge graphs, GraphRAG, and hybrid retrieval based on specific product requirements.
  • → Select the most suitable data access approach, including conventional APIs and alternative solutions, based on business needs and technical considerations.
  • →Establish mechanisms for data provenance, source attribution, knowledge grounding, and information freshness across enterprise data systems.
  • →Implement retrieval and answer evaluation practices to help consuming applications assess information quality, reliability, and origin.
  • →Collaborate with AI and application engineering teams to understand requirements while maintaining data ownership and access controls.
  • →Establish governance for semantic models and knowledge assets, covering ownership, documentation, versioning, change control, validation, and backward compatibility.
  • → Align internal product and business models with relevant industry standards, including GS1 identifiers and vocabularies, GPC, GDSN, GS1 Web Vocabulary, and schema.org Product, where applicable.
  • →Define and monitor data quality standards covering completeness, consistency, uniqueness, validity, freshness, lineage, and reconciliation.
  • → Develop automated validation and regression checks for schemas, mappings, ontology constraints, graph relationships, ingestion pipelines, and downstream contracts.
  • →Work with business domain owners to resolve ambiguity, manage changes in business meaning, and ensure semantic models accurately reflect organizational operations.
  • →Build and maintain semantic data services and pipelines with appropriate monitoring, tracing, alerting, debugging, regression testing, deployment, rollback, and capacity management. 
  • →Investigate failures, data anomalies, stale information, incorrect entity matches, and unexpected query behavior before they significantly affect customers or downstream applications.
  • →Optimize graph and data platform performance, scalability, availability, and operating costs based on actual usage and service requirements.
  • →Use customer feedback, data consumer input, and operational metrics to continuously improve semantic models, pipelines, and platform performance.
  • →Translate business requirements from category, R&D, supply chain, product, commercial, and data teams into clear semantic engineering priorities and delivery plans.
  • → Partner with Product, Data, AI, and Engineering leaders to identify opportunities for improving user experience, decision-making, analytics, and AI-enabled workflows.
  • →Own delivery outcomes across technical quality, data correctness, project scope, timelines, operational readiness, and stakeholder alignment.
  • →Measure success through improved data consistency, entity matching accuracy, reduced integration effort, and faster onboarding of data sources.
  • →Ensure reliable service performance and increased adoption across consuming applications.
  • →Communicate complex data and architecture decisions in clear business terms, ensuring technical and non-technical stakeholders understand trade-offs, dependencies, and risks.
  • →Apply a security-first engineering approach by incorporating realistic threat models, trust boundaries, data sensitivity, vulnerabilities, attack vectors, and business impact into system design.
  • →Identify and address security risks across the complete data lifecycle, including ingestion, storage, graph queries, APIs, AI-agent access, infrastructure, and third-party integrations.
  • →Establish secure engineering practices covering identity and access management, authentication, authorization, least-privilege access, and secrets management.
  • →Ensure secure data handling through encryption, data privacy, tenant isolation, and secure API and data access design.
  • →Identify and address security risks related to connected enterprise knowledge, including unauthorized relationship discovery, sensitive data inference, cross-tenant exposure, and data leakage.
  • →Ensure appropriate controls against excessive AI-agent permissions, unauthorized access, and misuse of retrieved information.
  • →Embed security practices into architecture and model reviews, code reviews, automated testing, CI/CD, production monitoring, and incident response.


Location & Eligibility

Where is the job
Islamabad, Pakistan
On-site at the office
Who can apply
PK

About this job

Who can apply
Pakistan
Posted
Today
Employer
has 141 open jobs on Jobera in 5 countries.

Listing Details

First seen
November 20, 2026
Last seen
November 20, 2026

Posting Health

Days active
0
Repost count
0
Trust Level
56%
Scored at
November 20, 2026

Signal breakdown

freshnesssource trustcontent trustemployer trust
Newsletter

Stay ahead of the market

Get the latest job openings, salary trends, and hiring insights delivered to your inbox every week.

A
B
C
D
Join 12,000+ marketers

No spam. Unsubscribe at any time.

Senior Semantic Engineer - Knowledge Graphs (Hybrid, Islamabad)