AI Enabled Modernization - Agentic Software Engineer - Vice President (New York, NY)

Goldman Sachs•New York, NY

1d•Onsite

About The Position

At Goldman Sachs, our Engineers don’t just make things – we make things possible. Change the world by connecting people and capital with ideas. Solve the most challenging and pressing engineering problems for our clients. Join our engineering teams that build massively scalable software and systems, architect low latency infrastructure solutions, proactively guard against cyber threats, and leverage machine learning alongside financial engineering to continuously turn data into action. Create new businesses, transform finance, and explore a world of opportunity at the speed of markets. Goldman Sachs Engineers are innovators and problem-solvers, building solutions in Artificial Intelligence, risk management, big data, mobile and more. We are seeking entrepreneurial Agentic Software Engineers to join a newly formed AI Agentic Systems team. This team is tasked with solving firmwide, large-scale application and infrastructure challenges by building and deploying swarms of agents. You will build systems that understand, plan, transform, and validate application modernization workflows across one of the largest and most complex technology estates in the industry. As a founding member of this team, you will help incubate a new paradigm of software engineering—moving beyond static automation to dynamic, goal-oriented agentic systems that operate across all the firm’s business units.

Requirements

Software Engineering Excellence: Strong proficiency in Python, Go, Java, Javascript or similar languages with a deep understanding of distributed systems and cloud-native architecture (AWS, Azure, or internal private clouds).
Agentic Experience: Direct experience deploying and operating LLM-based agents in production environments. Familiarity with frameworks such as LangGraph, AutoGPT, or custom-built orchestration layers.
AI Evals: Experience designing benchmarks, evaluations, and quality metrics for AI systems.
Problem-Solving Domains: Proven track record of applying agentic patterns to at least two of the following: Data Analysis: Autonomous synthesis of large-scale datasets. Observability: Self-healing infrastructure and automated root-cause analysis. Optimization: Dynamic resource allocation and cost management. Planning: Multi-step task decomposition and execution in non-deterministic environments.
Entrepreneurial Mindset: Ability to thrive in a 0-to-1 environment, comfortable with ambiguity, and driven to build systems that have never existed before.

Nice To Haves

Demonstrated interest in emerging agentic technologies such as Multi-Agent Reinforcement Learning (MARL), and swarm intelligence, with a willingness to experiment, learn, and apply new approaches where they create practical business value.
Familiarity with Model Context Protocol (MCP), A2A and other emerging standards for agent-to-tool communication.
Strong communication skills to bridge the gap between technical agentic logic and human-centric business processes.

Responsibilities

Agentic Orchestration: Design and deploy multi-agent systems (swarms) capable of autonomous planning, reasoning, and execution across distributed cloud environments.
Learning and Feedback: Build human-in-the-loop systems, evaluation frameworks, and observability mechanisms that enable continuous agent improvement.
Tool Integration: Design and build integrations with APIs, developer tooling, CI/CD pipelines, data platforms, or operational systems.
Cross-Functional Collaboration: Partner with diverse business units to identify high-impact use cases for agents, translating ambiguous business needs into technical agentic workflows.