What We DoAt Goldman Sachs, our Engineers don't just make things — we make things possible. The WM Data Engineering team within Asset & Wealth Management builds the cloud-native data platform that underpins Wealth Management globally — spanning Lakehouse architecture on AWS, ETL/ELT pipelines, data governance, and AI-powered tooling that accelerates how we build and operate at scale.Our AI Solutions Engineering function designs and delivers intelligent agent-based workflows and LLM-powered applications that transform how engineers and business teams work across the WM Data ecosystem.Who We Look ForWe are seeking a motivated AI Solutions Engineer to contribute to the design and delivery of production AI systems within a data engineering organization. You are intellectually curious, write clean tested code, and are excited about building AI applications at the intersection of large language models and real-world data infrastructure.ResponsibilitiesBuild and maintain AI-powered data engineering tools — LLM agents for pipeline generation, schema mapping, data quality analysis, and migration — integrated with the WM data platform (S3, Databricks, Snowflake, Glue, Athena, MWAA)Build and iterate on evaluation frameworks (LangSmith, RAGAS, PromptFoo) to measure and improve AI output quality across data engineering workloadsWrite well‑tested, production‑quality code with comprehensive unit and integration tests for AI componentsImplement responsible AI practices in every system: output guardrails, prompt injection defenses, PII handling, and audit logging — especially critical when operating on sensitive financial dataImplement and maintain backend services and APIs that expose AI‑driven data tooling platform engineers and internal stakeholdersCollaborate with senior engineers, data architects, and business stakeholders to scope requirements, prototype solutions, and ship iterativelyActively seek feedback, grow technical breadth across AI and data engineering, and contribute to team knowledge‑sharingBasic Qualifications3+ years of software engineering experience, including hands‑on work with machine learning models or AI application developmentProficiency in Java, Python, and SQL; hands‑on experience with LLM APIs or agentic frameworks (OpenAI, Anthropic, LangChain, or similar)Familiarity with agentic patterns: tool use, multi‑step reasoning, and structured output generationUnderstanding data engineering concepts — ETL/ELT pipelines, data warehousing, data lake architectures, or cloud data services (S3, Glue, Databricks, Snowflake, Athena)Awareness of responsible AI concerns — prompt injection, hallucination risk, output guardrails, data leakageStrong analytical and problem‑solving skills; effective written and verbal communicationPreferred QualificationsExperience with AI evaluation frameworks (LangSmith, RAGAS, PromptFoo, or equivalent)Familiarity with AWS AI/ML services (Bedrock, SageMaker, Lambda)Familiarity with Model Context Protocol (MCP) or similar standards for tool integration with LLM agentsExposure to pipeline orchestration tools (Airflow/MWAA, Step Functions) or Lakehouse patterns (Iceberg, Databricks, Snowflake)Experience in financial services or regulated data environmentsGoldman Sachs is an equal opportunity employer and does not discriminate on the basis of race, color, religion, sex, national origin, age, veterans status, disability, or any other characteristic protected by applicable law.#J-18808-Ljbffr