Overview

About Vanguard Founded in 1975, Vanguard is one of the world's leading investment management companies.

Responsibilities

• Lead the architecture, development, and delivery of scalable Generative AI, Retrieval-Augmented Generation (RAG), agentic AI, Knowledge Graph, and AI-enabled data solutions.
• Translate business requirements into secure, scalable, and maintainable solutions using the appropriate combination of AI, data engineering, APIs, graph technologies, and deterministic software.
• Design governed, AI-ready data pipelines and reusable AI services, APIs, agent tools, retrieval components, and engineering frameworks.
• Architect secure RAG and Knowledge Graph solutions encompassing document processing, embeddings, vector and graph search, metadata, reranking, entity and relationship modeling, Graph-RAG, citations, and access controls.
• Design agentic workflows using tool and function calling, structured outputs, state and memory management, and multi-step orchestration.
• Establish AI evaluation and responsible AI practices covering groundedness, retrieval quality, hallucination, tool execution, privacy, security, guardrails, human oversight, latency, and cost.
• Define engineering and operational standards for CI/CD, automated testing, infrastructure as code, monitoring, observability, release readiness, and production support.
• Evaluate AI models, platforms, frameworks, and technical approaches based on quality, security, performance, scalability, maintainability, and cost.
• Provide technical leadership through architecture, design, and code reviews, mentoring, complex troubleshooting, and engineering guidance.
• Lead production incident resolution, root-cause analysis, preventive actions, release support, and reliability improvements for business-critical AI and data solutions.
• Drive continuous improvement through reusable engineering patterns, automation, operational learnings, and responsible use of approved AI-assisted development tools, including Claude Code and GitHub Copilot.

Qualifications

• Minimum 8 years of relevant technology experience, with significant hands-on experience in software engineering, AI engineering, machine learning engineering, or data engineering.
• Bachelor’s degree in Computer Science, Information Technology, Engineering, Computer Applications, Data Science, or a related discipline from a recognized institution.
• Demonstrated experience designing and delivering AI or Generative AI applications into production.
• Strong experience architecting production-grade LLM applications using prompt and context engineering, RAG, agentic workflows, tool/function calling, structured outputs, and Model Context Protocol (MCP).
• Strong experience with AI platforms and frameworks such as Amazon Bedrock, LangChain, LangGraph, or comparable technologies.
• Hands-on experience with Knowledge Graph technologies such as Amazon Neptune, Neo4j, or similar platforms, including ontology/schema design, entity and relationship modeling, Graph-RAG, and query languages such as Gremlin, Cypher, or SPARQL.
• Advanced proficiency in Python, PySpark, Pandas, SQL, REST APIs, and secure software-engineering practices.
• Strong data engineering experience with scalable data pipelines, ETL/ELT frameworks, structured and unstructured data processing, cloud data platforms, and distributed data-processing solutions.
• Experience with technologies including AWS Glue, Amazon S3, Redshift, Athena, Spark, Databricks, Airflow/Step Functions, and Kafka/Kinesis.
• Strong experience with enterprise search and retrieval solutions using OpenSearch Serverless, vector databases, embeddings, document chunking, metadata filtering, reranking, access controls, and retrieval-evaluation techniques.
• Experience defining AI evaluation strategies encompassing groundedness, retrieval relevance, hallucination, tool execution, security, privacy, latency, cost, guardrails, and human oversight.
• Strong experience with Docker, Terraform/AWS CDK, Git, CI/CD, automated testing, monitoring, tracing, alerting, and observability.
• Demonstrated experience with production support, incident management, root-cause analysis, operational readiness, release support, and reliability improvement for AI, data, or software solutions.
• Experience using approved AI-assisted engineering tools such as Claude Code and GitHub Copilot for coding, testing, debugging, documentation, and modernization.
• Demonstrated ability to lead architecture, design, and code reviews, evaluate technical alternatives, establish reusable engineering patterns, mentor engineers, and troubleshoot complex technical issues.
• Strong product mindset with the ability to connect AI and technology decisions to meaningful business and customer outcomes.
• Ability to determine where AI is appropriate and where deterministic software or conventional data engineering represents the better solution.
• Ability to clearly explain probabilistic AI behavior, technical risks, trade-offs, and evaluation results to both technical and non-technical stakeholders.
• Strong analytical, problem-solving, debugging, and root-cause analysis capabilities.
• Experience working in Agile product environments with strong ownership, accountability, and stakeholder engagement.
• Ability to manage ambiguity, competing priorities, dependencies, and rapidly evolving AI technologies.
• Commitment to responsible AI, privacy, security, engineering excellence, and continuous learning.
• Willingness to support critical production incidents and releases outside regular working hours when needed.