Alpha Business Process Automation(RAG Engineer), Assistant Manager
State Street CorporationMatch Score
Against your primary resumeLogin to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Protocol Intelligence
Data-driven signals on your job's competitivenessNiche Knowledge Graph and RAG specialization reduces applicant density despite the strong employer brand.
Specialized graph-RAG and enterprise AI skills are transferable but favor regulated enterprise experience.
Explicit 7–12 years plus numerous mandatory graph, RAG, and Python production skills enforce strict filters.
Job Description
Structured overview of role & requirementsAbout This Role
Design, develop, integrate, test, deploy, and support enterprise-scale ontologies, Knowledge Graphs, RAG and Graph RAG capabilities, focusing about 80% on core knowledge and retrieval engineering.
Build and enhance RAG and Graph RAG pipelines using hybrid retrieval techniques including vector search, semantic search, graph traversal, and source attribution with a focus on improving solution quality and reliability.
Develop Python APIs/microservices, collaborate with cross-functional teams, and support cloud-native AI agent orchestration and governance capabilities (about 20% focus).
Minimum Requirements
7 to 12 years of overall technology experience with 3+ years hands-on in enterprise data, semantic, graph, search, knowledge, or AI solutions.
Strong hands-on experience with ontology design, semantic models, graph platforms (e.g., Neo4j, Amazon Neptune), and query languages like Cypher or SPARQL.
Proficiency in building ingestion and transformation pipelines for structured and unstructured content and implementing RAG/Graph RAG solutions involving embeddings, vector indexing, and entity extraction.
Bachelor's degree in Computer Science, Engineering, AI, Data Science, or related discipline. Notice period: Not explicitly mentioned in the JD.
Ideal Candidate Profile
Experienced in delivering Knowledge Graph, Ontology, RAG, Graph RAG, Agentic AI, or Generative AI solutions through all lifecycle phases including production implementation.
Operates with strong ownership and pragmatic architecture focus, emphasizing secure, reliable, measurable, and governed enterprise AI outcomes.
Comfortable collaborating across architects, product owners, AI engineers, and application teams to translate business needs into reusable semantic and retrieval capabilities.