Data Engineer (SMTS/LMTS) - Knowledge Graph & AI

Overview

Salesforce stands as a leader in AI powered customer relationship management, driven by teams of agents delivering customer success. We seek ambitious professionals who want to advance business and society through AI while upholding Salesforce’s core values. If you are excited about the future of AI in enterprise settings, this opportunity is for you.

The Opportunity

Salesforce is building the next generation Enterprise Knowledge Graph platform to empower AI driven experiences, agent centered applications, semantic search, enterprise data discovery, and intelligent decision making across the organization. We are hiring for both a Senior Member of Technical Staff (SMTS) and a Lead Member of Technical Staff (LMTS) to join the Enterprise Knowledge Graph and AI Engineering team.

Your Responsibilities

• Design and Implement: Develop and scale the Enterprise Knowledge Graph platform components with a focus on performance, throughput, reliability, high availability, and data integrity. LMTS leads hands on design and subsystem implementation; SMTS contributes production grade code.
• Graph and Ontology Engineering: Create graph data models, craft complex queries, and build scalable data pipelines to map structured and unstructured data to enterprise ontologies and taxonomies. LMTS also designs enterprise ontologies, taxonomies, semantic layers, entity resolution frameworks, graph APIs, and vector search capabilities to support advanced RAG and agentic workflows.
• Semantic Routing: Develop Python based semantic routing frameworks to parse, classify, and dynamically direct incoming queries to the appropriate knowledge graph indexes or vector databases. LMTS designs, optimizes, and productionizes routing frameworks at scale, steering queries to relevant graphs, ontology subgraphs, or vector stores.
• AI Tooling and Automation: Build and integrate AI powered developer tools and engineering automation platforms leveraging ecosystems such as Claude, Cursor, Windsurf, AI Agents, and Model Context Protocol (MCP) frameworks. LMTS also develops, deploys, and optimizes these tools and drives strategy and productionization.
• Data Integration: Create scalable data pipelines and engineering patterns to ingest, transform, and orchestrate structured, unstructured, and third party data sources into graph based platforms mapped to enterprise ontologies.
• Feature Ownership and Technical Execution: Own the technical delivery of specific platform features from concept through design, coding, testing, and production deployment. LMTS translates high level technical visions into concrete system blueprints, ontology schemas, and execution plans.
• Code Quality and Rigor: Engage in code reviews, write comprehensive automated unit and integration tests, and uphold engineering standards and operational best practices.
• Technical Mentorship: Provide technical guidance to the engineering team. SMTS mentors MTS and Associate engineers; LMTS offers day-to-day guidance, code reviews, and design direction to SMTS, MTS, and associated engineers to foster technical rigor and operational maturity.
• Cross-Functional Collaboration: Work closely with Lead and Principal Engineers, Product Managers, and Data Engineering teams to deliver robust features aligned with enterprise AI priorities. LMTS also partners with PMTS engineers and Ontology governance boards to ensure alignment with AI infrastructure standards.
• Evaluate and Innovate: Conduct deep dive evaluations of emerging graph technologies, ontology modeling tools, semantic reasoning frameworks, vector databases, and AI tooling to continuously modernize the platform.

You're Our Person If

SMTS

• Experience: 8+ years of hands on software engineering experience in development, data engineering, distributed systems, or enterprise data platforms.
• Education: A related technical degree is required.
• Core Programming: Expert level backend coding skills with strong fluency in Python and standard object oriented or functional programming languages.
• Semantic Routing and AI: Hands on experience building and deploying custom semantic routers using Python, embeddings, LangChain, or cosine similarity, alongside Retrieval-Augmented Generation architectures, vector search platforms, and AI workflows.
• Graph and Ontology Fundamentals: Solid experience with graph databases and semantic web concepts such as Neo4j, RDF/OWL, SPARQL, and property graphs, mapping data to structured taxonomies.
• Developer Tooling: Practical experience configuring, testing, or integrating AI-assisted engineering tools or automation workflows such as Claude, Cursor, Windsurf, GitHub Copilot, or MCP frameworks.
• Distributed Systems and Cloud: Proven ability to build cloud native applications on AWS, GCP, or Azure using microservices, REST or gRPC APIs, and event driven data streaming (Kafka).
• Delivery: A track record of owning and delivering complex features in an agile production environment.

LMTS

• Experience: 10+ years of hands-on experience in software engineering, data engineering, distributed systems, or enterprise data platforms.
• Education: A related technical degree is required.
• Ontology and Graph Expertise: Substantial hands-on experience designing and building Knowledge Graph platforms, formal ontologies, semantic models, taxonomies, or enterprise metadata management systems.
• Tooling and Ecosystems: Strong hands-on experience with graph technologies and ontology engineering tools such as Neo4j, TopQuadrant, Protégé, RDF/OWL, SPARQL, SHACL, property graphs, and semantic reasoning frameworks.
• AI and Retrieval: Proven experience implementing graph powered AI solutions, vector search platforms, Retrieval-Augmented Generation architectures, and orchestrating agentic workflows.
• Semantic Routing Mastery: Demonstrated hands-on experience designing, optimizing, and productionizing custom semantic routing.

Location

San Francisco, California 94105