Senior Graph Engineer (Python)

About Us:

We are an innovative AI startup focused on transforming professional services through Generative AI and deep domain expertise. Our agent-driven solutions automate complex workflows, engaging humans when needed to maximize efficiency and accuracy. Join us to build the knowledge infrastructure that connects enterprise information and powers intelligent applications.

Role Overview:

We are looking for an experienced Python engineer with deep expertise in graph technologies and knowledge representation to join our Data & Knowledge team. As a Senior Graph Engineer, you will lead the design, development, and deployment of graph-based systems that connect structured and unstructured data, support complex queries, and improve AI retrieval and reasoning. You will work closely with AI engineers and domain experts to turn enterprise information into reliable, actionable knowledge.

Key Responsibilities:

• Graph Architecture and Modeling:  Design and build scalable knowledge graphs, defining schemas, ontologies, entities, and relationships that reflect complex business domains.
• Data Integration:  Build pipelines that extract, normalize, and connect data from documents, databases, and external systems, with support for incremental updates.
• Entity Resolution and Data Quality:  Implement entity matching, deduplication, relationship validation, and provenance tracking to maintain trustworthy graph data.
• Graph Retrieval and AI Integration:  Develop graph-based retrieval capabilities and integrate them with vector search, RAG systems, and AI agents.
• Performance and Reliability:  Optimize graph queries, indexing, and storage; implement testing, monitoring, access controls, and recovery practices.
• Python Development:  Develop production-grade services, APIs, and pipelines for graph ingestion, querying, and integration with enterprise applications.

Qualifications:

Experience:

• 6+ years of professional software engineering experience, with strong expertise in Python.
• 2+ years of hands-on experience developing graph-based applications, knowledge graphs, or graph data platforms 

• Ideally, experience using knowledge graphs in AI/agentic applications to support graph or hybrid Graph-RAG retrieval 

Education:

• Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field, or equivalent practical experience.

Technical Skills:

• Advanced proficiency in Python and libraries like NetworkX, Pandas, NumPy, or similar.
• Strong understanding of graph data modeling, graph traversal, indexing, and query optimization.
• Hands-on experience with a graph database such as Neo4j, Amazon Neptune, or Azure Cosmos DB for Apache Gremlin.
• Proficiency in a graph query language such as Cypher, Gremlin, or SPARQL, with an understanding of property graph or RDF models.
• Experience building data ingestion and transformation pipelines across structured and unstructured sources.
• Familiarity with entity resolution, ontology design, data lineage, and graph data quality practices.
• Familiarity with knowledge graphs in AI applications, including GraphRAG, hybrid graph and vector retrieval, or agent tools, is a plus.

Soft Skills:

• Excellent communication skills, including the ability to explain graph concepts and technical tradeoffs to nontechnical stakeholders.
• Strong analytical and problem-solving skills, with attention to data quality and system reliability.
• Ability to own projects from design through deployment and collaborate across disciplines.
• Comfortable navigating ambiguity and evolving priorities in a fast-paced startup.

Benefits

• Competitive Compensation:  Tailored to your experience and skill set.
• Flexible Work Arrangements:  Hybrid working model for work-life balance.
• Career Growth:  Opportunities for professional development and technical leadership.
• Innovative Culture:  Build technologies that connect enterprise knowledge and power the next generation of AI applications.