Skip to main content

Software Engineer, Global Investment Research, Agentic Systems - Associate

Posted today

goldman sachsDallas (TX)

SENIORITY

Lead

Apply (opens in a new tab)

About the role

Overview: In this role, you will help build and productionize intelligent research tools and automated agentic pipelines within GIR, collaborating with senior engineers to deliver end-to-end AI-enabled features. You will integrate frontends with backend services, develop RAG-based workflows, and connect AI components to enterprise systems in a scalable, secure cloud environment. The work combines research with practical deployment, driving AI-enabled insights for financial research at scale. You will operate in a fast-paced, cross-functional setting that values impact and hands-on problem solving.
Responsibilities: Build and maintain end-to-end full-stack features tying analyst-facing frontends to backend APIs/microservices (Java or Python) Implement and optimize RAG pipelines and multi-agent workflows using agentic frameworks and cloud services Design and run automated evaluation suites to benchmark contextual relevance, groundedness, and hallucination reduction Deploy and connect AI components to enterprise services on AWS (Lambda, ECS/Fargate, S3, IAM, API Gateway) Monitor performance and incidents using observability tools; perform root-cause analyses and optimize resource usage Participate in SDLC processes: code reviews, automated tests, CI/CD, and documenting integration patterns Coordinate with stakeholders in Agile sprints to translate research into deliverable stories
Key requirements: Bachelor’s degree in Computer Science, Software Engineering, Applied Mathematics, or a related quantitative field 3–5 years of hands-on software engineering experience with Java or Python Experience with modern full-stack web technologies (React, TypeScript, FastAPI, Spring Boot) Practical experience building Gen AI apps using Google ADK, LangGraph, or equivalent frameworks, vector databases, and AWS Bedrock Experience building evaluation pipelines and prompt testing (Braintrust, AgentCore Eval, or equivalents) Working knowledge of AWS services (Lambda, ECS/Fargate, S3, EventBridge, CloudWatch, API Gateway) Solid understanding of SDLC tooling, automated testing, Git, Docker, and CI/CD automation Agile collaboration cross-functional teamwork ability to translate research requirements into deliverable stories Java Python React

Before you apply

Applying takes about a minute. These four things decide how fast it moves after that.

Your profile is current

It's what we read first. Occupations, seniority and locations matter more than a long history.

Two examples you can talk through

Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.

A number in mind

What you're on now and what would make you move. We negotiate better when we know both.

Your notice period

Employers plan around it, and it's the question that stalls offers most often.

Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.

More like this