Senior AI Engineer (Java/JVM) - RAG & Agentic Workflows

Goldman Sachs; New York (NY); On-site; USD 150,000 - 300,000; Full time

Job summary

Goldman Sachs is seeking a Senior AI Engineering Expert to architect and implement production-grade AI solutions within our Java-based microservices ecosystem. You will build scalable AI workflows, optimize latency, and ensure governance and compliance across enterprise data pipelines.

You will lead cross-functional efforts to modernize traditional Java processes into real-time AI architectures, leveraging AWS MSK and vector databases while ensuring explainability and auditability in

Qualifications

• 6+ years in Java software engineering, with at least 3 years focused on AI/ML integration in production.
• Experience with RIA workflows and collateral regulatory landscape is a plus.
• Deep knowledge of Java/JVM ecosystems and enterprise microservices.

Responsibilities

• Architect end-to-end AI pipelines (RAG, Agentic workflows) that integrate with APIs, databases and microservices.
• Optimize inference latency and manage token costs for large-scale deployments.
• Establish evaluation frameworks to measure model accuracy and guard against hallucinations.
• Collaborate with tech leads, security, and software teams to define AI roadmaps.
• Stay ahead in Generative AI and autonomous agents, recommending pivots as needed.
• Build enterprise RAG pipelines using Java-based ETL to index data into vector stores.
• Monitor LLM latency, token usage, and model drift using Spring Boot Actuator and Micrometer.
• Implement HITL patterns and structured logging for auditable, compliant decisions.

Skills

Java 21+

AI frameworks

Spring Boot 3.x

SQL

Kafka or RabbitMQ

AWS

Vector stores integration

Education

Degree in Computer Science or related field

Tools

Milvus

Weaviate

Pinecone

Job description

Goldman Sachs is seeking a Senior AI Engineering Expert to architect and implement production-grade AI solutions within our Java-based microservices ecosystem. You will build scalable AI workflows, optimize latency, and ensure governance and compliance across enterprise data pipelines.

You will lead cross-functional efforts to modernize traditional Java processes into real-time AI architectures, leveraging AWS MSK and vector databases while ensuring explainability and auditability in