Lead/Sr. Semantic Engineer/Knowledge Graph Engineer

The posting

About the role

We’re looking for a Lead/Senior Semantic Engineer / Knowledge Graph Engineer who combines strong software engineering fundamentals with deep understanding of enterprise data, semantic modeling, and how software is built in the age of AI. This is a senior technical leadership role for someone who can set direction, build strong semantic engineering capabilities, and shape how product, commercial, customer, and operational knowledge is modeled, connected, governed, and made useful across the business.

You will lead the design and evolution of semantic data capabilities that may require connecting RGM/TPM product, commercial, consumer, retailer, supply chain, and enterprise data. These capabilities may include knowledge graphs, ontologies, taxonomies, canonical business models, entity resolution, semantic interfaces, and data products that power analytics, search, the digital shelf, and AI-enabled applications. You will work closely with R&D, Product, Data, and Engineering teams to ensure that enterprise knowledge reflects real business concepts and can be reliably consumed by applications and AI agents.

The central expectation is not simply to build a graph or adopt a particular semantic technology. It is to solve complex enterprise knowledge problems with sound engineering judgment: understand the business meaning of data, choose the right representation and architecture, make information trustworthy and interoperable, and operate the resulting capabilities reliably. You will also help rethink the semantic engineering lifecycle using AI coding agents and automation, improving how the team discovers, models, implements, validates, documents, and maintains semantic capabilities while retaining clear human ownership and accountability.

What you will lead and deliver

1. Build and manage an AI-native semantic engineering capability

· Define and continuously improve how semantic engineering work is carried out across discovery, domain analysis, modeling, implementation, data integration, testing, documentation, deployment, and operations.

· Establish practical patterns for using AI coding agents and other AI tools to accelerate ontology development, schema mapping, data profiling, transformation development, test generation, documentation, and engineering workflows.

· Design workflows in which engineers can delegate well-defined tasks to AI agents while maintaining human review of business meaning, model integrity, data quality, security, and production changes.

· Increase the team's delivery capacity through automation, reusable semantic assets, shared tooling, better domain context, and agent-enabled workflows—not simply by increasing headcount.

· Set expectations for responsible and effective use of AI: understand where agents add value, provide them with the right context, validate their outputs, and know when human judgment is essential.

2. Provide technical and engineering leadership

· Set the technical vision, architecture direction, and engineering standards for enterprise semantic models, knowledge platforms, graph services, and data integrations.

· Lead by example through hands-on technical contribution, architecture and model reviews, design discussions, code reviews, and resolution of complex engineering challenges.

3. Architect and deliver enterprise semantic capabilities

· 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 that enable consistent interpretation and interoperability across enterprise applications.

· Design knowledge graph and semantic data architectures that connect product, customer, retailer, supply chain, pricing, promotion, RGM/TPM, and retail execution domains across enterprise systems.

· Choose appropriate representations and technologies, including RDF, OWL, SKOS, property graphs, relational models, search indexes, or combinations of these, based on the business problem, interoperability needs, 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.

· Enable reliable entity resolution and master data reconciliation 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, allowing enterprise applications and AI agents to securely consume business entities, context, and relationships.

· Support business use cases such as analytics, search, recommendations, digital shelf, product traceability, ingredient and allergen traceability, labeling compliance, and packaging/ESG reporting.

4. Enable AI applications with trustworthy enterprise knowledge

· Make enterprise knowledge accessible and useful to AI-enabled applications and agents through well-defined, governed, and reliable interfaces.

· Evaluate and apply retrieval, semantic search, vector search, knowledge graphs, GraphRAG, and hybrid approaches when they demonstrably improve a use case; do not treat any one pattern as a default solution.

· Establish mechanisms for data provenance, source attribution, knowledge grounding, freshness, and retrieval or answer evaluation so consuming applications can assess the quality and origin of information.

· Work with AI and application engineering teams to understand agent and application requirements, expose the appropriate business context, and prevent consumers from bypassing data ownership or access controls.

· Help determine when structured semantic models, conventional APIs, search, or other data access patterns are the most effective way to support a product capability.

5. Establish semantic governance and data quality

· Establish practical governance for semantic models and knowledge assets, including ownership, documentation, versioning, change control, validation, and backward compatibility.

· Define and monitor data quality expectations covering completeness, consistency, uniqueness, validity, freshness, lineage, and reconciliation.

· Create automated validation and regression checks for schemas, mappings, ontology constraints, graph relationships, ingestion pipelines, and downstream contracts.

· Align internal product and business models with relevant industry standards such as GS1 identifiers and vocabularies, GPC, GDSN, GS1 Web Vocabulary, and schema.org Product where they provide value.

· Work with business domain owners to resolve ambiguity, manage changes in business meaning, and ensure that semantic models reflect how the organization actually operates.

6. Ensure production quality and operational excellence

· Build semantic data services and pipelines that are monitored well enough for the team to identify data, integration, and performance issues before they materially affect customers or downstream applications.

· Understand how semantic capabilities behave in production and be able to explain failures, data anomalies, stale information, incorrect entity matches, and unexpected query behavior using operational evidence.

· Establish practices for tracing, monitoring, alerting, debugging, regression testing, deployment, rollback, capacity management, and continuous improvement.

· Optimize graph and data platform performance, scalability, availability, and operating cost based on real usage and service requirements.

· Use feedback from customers, data consumers, and operational metrics to systematically improve semantic models, data pipelines, and platform behavior.

7. Drive execution and business outcomes

· Translate business needs 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 where connected enterprise knowledge can improve user experience, decision-making, analytics, and AI-enabled workflows.

· Own delivery outcomes across technical quality, data correctness, scope, timelines, operational readiness, and stakeholder alignment.

· Measure success through business and engineering outcomes such as improved data consistency, entity match quality, reduced integration effort, faster onboarding of data sources, reliable service performance, and adoption by consuming applications.

· Communicate complex data and architecture decisions in clear business terms, making trade-offs, dependencies, and risks understandable to technical and non-technical stakeholders.

8. Security Engineering & Threat Management

· Demonstrate a strong security-first engineering mindset, with a deep understanding of information security principles, threat modeling, and secure-by-design architecture.

· Identify, assess, and proactively address security threats across semantic platforms and the full data lifecycle, including ingestion, storage, graph queries, APIs, AI-agent access, infrastructure, and third-party integrations.

· Design systems based on realistic threat models, understanding attack vectors, trust boundaries, data sensitivity, vulnerabilities, and potential impact rather than relying on superficial security controls or compliance checklists.

· Establish secure engineering practices covering identity and access management, authentication, authorization, least-privilege access, secrets management, encryption, data privacy, tenant isolation, and secure API and data access design.

· Pay particular attention to risks arising from connected enterprise knowledge, including unauthorized relationship discovery, sensitive data inference, cross-tenant exposure, excessive agent permissions, data leakage, and misuse of retrieved information.

· Embed security into architecture and model reviews, code reviews, automated testing, CI/CD, production monitoring, and incident response.

What we are looking for

· Strong software engineering and data engineering fundamentals. You understand how to design, build, test, secure, deploy, and operate reliable data-intensive systems, and can demonstrate sound judgment in architecture, APIs, data modeling, distributed systems, debugging, and technical trade-offs.

· A strong understanding of data semantics: how business concepts, entities, relationships, identifiers, definitions, and context should be represented consistently across systems.

· Practical experience with at least one approach to semantic modeling or knowledge representation, such as RDF/OWL/SKOS, property graphs, canonical data models, domain models, or equivalent techniques. Deep expertise in every standard or framework is not expected.

· Experience designing or building data integration, transformation, synchronization, or entity-resolution capabilities across multiple enterprise systems.

· Ability to translate ambiguous business requirements into clear domain models, data contracts, and implementable engineering solutions, working directly with business and technical stakeholders.

· Demonstrated ability to use AI coding tools and agents effectively in real engineering work. You understand their strengths and failure modes and can integrate them into disciplined workflows.

· Evidence of improving engineering throughput or delivery capacity through automation, reusable systems, tooling, process redesign, or agent-enabled execution.

· Experience with graph databases, triple stores, relational databases, search platforms, or other data storage technologies, with the ability to evaluate trade-offs rather than default to a specific product.

· Proficiency in Python and another suitable programming language, and familiarity with building data pipelines, APIs, services, and automated tests. Azure data services are relevant to our environment.

· Understanding of data quality, data governance, lineage, provenance, model lifecycle management, and enterprise data security.

· Strong communication and collaboration skills, with the ability to work across Product, Business, Data, AI, and Engineering and explain technical decisions in clear, outcome-oriented language.

Useful experience

· Strong experience in software engineering, data engineering, or semantic engineering, preferably 8–10+ years, with demonstrated ability to lead complex technical work. We prioritize engineering depth, judgment, and evidence of impact over years of experience alone.

· Experience leading or contributing to a team that has increased delivery capacity through AI coding agents, automation, or redesigned engineering workflows.

· Experience designing production knowledge graphs, ontologies, taxonomies, semantic layers, or enterprise canonical data models.

· Familiarity with RDF, OWL, SKOS, SPARQL, SHACL, Protégé, TopBraid, or PoolParty.

· Experience with graph databases or triple stores, such as Neo4j, Amazon Neptune, GraphDB, Stardog, or equivalent platforms.

· Experience with entity resolution, record linkage, master data management, product information management, or data reconciliation.

· Experience with CPG, retail, manufacturing, product master data, supply chain, commercial, retailer, or syndicated market data.

· Familiarity with GS1 standards, including GTIN, GPC, GDSN, and GS1 Web Vocabulary, or schema.org Product.

· Experience integrating SAP S/4HANA or MDG and 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 solve a demonstrated product problem.

· Experience with Azure Data Factory, Azure Databricks, Microsoft Fabric, Synapse, Azure AI Search, Azure OpenAI, Azure DevOps, or Azure Kubernetes Service.

· Experience with event-driven architectures, streaming ingestion, change data capture, and operational monitoring of data platforms.

· Experience with NLP or AI-assisted extraction of product attributes and business knowledge from specifications, labels, and enterprise documents.

Education

A degree in Computer Science, Information Science, Data Engineering, or a related field may be helpful, but it is not a substitute for demonstrated engineering and problem-solving capability. Equivalent practical experience and a strong record of delivery are welcome.

What We Have For You

• Great compensation package, medical benefit for you and your family, free lunch, annual performance-tied increments & performance recognition awards and a great lean and agile work culture!
• Convo endorses a culture of diversity in all aspects and aims to build a diverse team of amazing individuals!