The Core Engineering-L2-Dallas-Vice President-Software Engineering
Goldman Sachs13 hours ago
Responsibilities
- Lead the design, build, deployment, and operationalization of cloud-native AI applications.
- Partner with business and engineering teams to identify AI opportunities and define scalable architectures, data models, and technical specifications.
- Embed with internal business teams to discover workflows, assess agentic automation opportunities, run pilots, and drive adoption.
- Integrate LLM APIs, retrieval-augmented generation, embeddings, vector search, prompt and context management, structured outputs, validation, and evaluation harnesses into production applications.
- Apply cloud-native services, secure deployment patterns, observability, lifecycle management, and MLOps practices.
- Document solutions, mentor receiving teams, and support transition of code, integrations, data models, and operational practices.
- Implement or optimize agentic AI systems, observability, controls, model routing, retrieval, caching, execution, cost, latency, and quality where applicable.
Requirements
- Bachelor’s or Master’s degree in Computer Science, Software Engineering, or a related quantitative field.
- At least 9 years of hands-on software engineering experience building, deploying, and supporting production applications.
- Strong proficiency in Python, Java, or Go, with sound software engineering, testing, data modeling, and system design skills.
- Experience translating complex business requirements into cloud-optimized architectures, scalable data models, and production specifications.
- Experience in forward-deployed or internal client-facing engineering, including workflow discovery, stakeholder engagement, prototyping, pilots, adoption measurement, and production handoff.
- Extensive experience with AWS, Azure, or GCP, including serverless, containerization, managed services, automated deployment, monitoring, and cloud security standards.
- Experience designing cloud-based AI architectures integrating managed AI services, LLM providers, retrieval and vector search, secure data access, API gateways, event-driven workflows, identity and entitlement controls, observability, deployment automation, and cost and resilience trade-offs.
- Experience integrating LLM or AI/ML capabilities into production applications, including RAG pipelines, embeddings, vector databases or search indexes, prompt templates, context assembly, structured outputs, response validation, evaluation datasets, and model performance monitoring.
- Excellent communication and collaboration skills with technical and non-technical stakeholders.
- Preferred experience building agentic AI systems with task decomposition, planning, tool and API calls, state management, permissions, failure handling, and auditable action trails.
- Preferred experience implementing agent observability and controls, including trace capture, logging, hallucination and policy checks, human-in-the-loop approvals, incident handoff, and post-action summaries.
- Preferred experience optimizing production AI systems through model selection and routing, prompt compression, retrieval tuning, caching, batching, streaming, asynchronous execution, parallel tool calls, latency budgets, cost controls, and quality regression testing.
Categories
AI ApplicationsForward Deployed
About Goldman Sachs
Goldman Sachs is a global financial services firm that provides investment banking, securities trading, and asset and wealth management to corporations, financial institutions, governments, and individuals. Its businesses generate revenue from advisory and underwriting fees, trading and financing, and management fees on client assets. Founded in 1869 and headquartered in New York City, it operates worldwide and is listed on the NYSE under the ticker GS.