Senior Engineer - RAG Engineering, Assistant Manager

Who we are looking for We are looking for a hands-on Senior Engineer with a proven track record of designing and implementing enterprise-scale Ontologies, Knowledge Graphs, Knowledge Layers, RAG and Graph RAG pipelines, Agentic AI solutions, AI orchestration frameworks, and cloud-native Generative AI capabilities.

Working with AI platform, enterprise architecture, data engineering, product, and application teams, you will focus on hands-on development, configuration, integration, testing, troubleshooting, and production support.

You will need deep experience in semantic technologies, graph databases, ingestion and retrieval pipelines, Python engineering, AWS Bedrock, and modern agent frameworks across cloud-native and enterprise environments.

Why this role is important to us Enterprise AI capabilities depend on trusted, connected, governed, and traceable knowledge.

Ontologies and Knowledge Graphs provide the semantic foundation, while RAG, Graph RAG, and Agentic AI make that knowledge accessible for intelligent search, impact analysis, operational support, onboarding, engineering productivity, and workflow automation.

This role is important in converting fragmented enterprise information into a reusable knowledge layer and building the technical services that allow AI applications and agents to retrieve, reason, cite sources, and execute approved actions reliably.

About the team — Alpha Intelligence Alpha Intelligence is State Street’s AI & Automation Center of Excellence for Alpha Implementations — the team rewiring how the industry’s first front-to-back platform gets delivered.

We turn the deep expertise locked inside our implementation teams into engineered processes, governed knowledge and intelligent agents that cut manual effort, compress client go-live timelines and make every implementation faster and more predictable than the last.

We operate as one global team across the North America, EMEA, and APAC, combining process engineering, automation delivery, AI platform engineering and responsible-AI governance under a single roof.

We work on real client implementations, not pilots that sit on a shelf — what we build is adopted, measured and scaled.

If you want to shape how AI is applied to one of the most complex delivery landscapes in financial services, this is the team to do it in.

What you will be responsible for This role will be responsible for hands-on design, development, integration, testing, deployment, and support of enterprise ontology, Knowledge Graph, RAG, and Graph RAG capabilities.

Approximately 80% of the role will focus on the core knowledge and retrieval engineering skills listed as must-have, while approximately 20% will involve agentic AI, cloud-native services, orchestration, security, and governance capabilities listed as nice-to-have.

Design and maintain ontologies, semantic models, metadata structures, taxonomies, entity types, relationship definitions, and validation rules using RDF, RDFS, OWL, SHACL, or labeled property graph approaches.

Model, build, enrich, and query enterprise Knowledge Graphs using platforms such as Neo4j, Amazon Neptune, Graph DB, or equivalent, with Cypher, SPARQL, or related graph query languages.

Develop ingestion and transformation pipelines for structured and unstructured enterprise content from documents, databases, APIs, and approved repositories.

Implement document parsing, chunking, metadata extraction, embeddings, vector indexing, entity and relationship extraction, entity resolution, provenance, lineage, and data-quality controls.

Build and enhance RAG and Graph RAG pipelines using hybrid retrieval, vector and semantic search, metadata filtering, graph traversal, reranking, grounding, source attribution, and citations.

Define and execute retrieval evaluation, groundedness testing, hallucination-reduction measures, observability, and performance tuning to improve solution quality and reliability.

Develop production-quality Python APIs and microservices with robust error handling, automated unit and integration tests, reusable components, and clear technical documentation.

Use Git and CI/CD practices to package, deploy, monitor, troubleshoot, tune, and support knowledge and retrieval services across enterprise environments.

Collaborate with architects, subject matter experts, data engineers, AI engineers, product owners, and application teams to translate business needs into reusable semantic and retrieval capabilities.

Participate in code reviews, Agile ceremonies, release activities, defect resolution, and production support while maintaining secure, reliable, and measurable engineering standards.

Develop or integrate AI agents with enterprise APIs, tools, knowledge repositories, and workflow services using frameworks such as Lang Chain, Lang Graph, Llama Index, Semantic Kernel, or equivalent.

Support single-agent or multi-agent orchestration, tool calling, memory, planning, routing, state management, human-in-the-loop controls, guardrails, and structured agent evaluation.

Configure or integrate AWS Bedrock Agents, Guardrails, foundation models, or equivalent cloud-native services, and contribute to containerization, serverless deployment, infrastructure as code, cloud security, responsible AI, privacy, access control, auditability, and governance practices.

What we value The successful candidate must have excellent verbal, written, and presentation skills and be able to communicate complex AI, graph, data, and architecture concepts to engineering teams, business stakeholders, and senior technology leaders.

The candidate should demonstrate strong ownership, structured problem solving, pragmatic architecture, reusable engineering, collaboration, and a consistent focus on secure, reliable, measurable, and governed enterprise AI outcomes.

Must-have skills Hands-on experience designing ontologies, semantic models, metadata structures, taxonomies, entity types, and relationship definitions.

Strong experience with at least one en