About The Position

State Street Investment Management’s Data, Analytics and AI Services team is seeking an AI Engineer – Agentic Systems to build, test, deploy, and measure agentic AI solutions that transform business workflows across the investment management organization. This hands-on engineering role takes defined and scoped AI use cases from prototype to production, creating reliable, governed, and auditable AI agents that connect to enterprise data and applications. The role addresses data readiness and integration challenges, builds rigorous evaluation and auditability into solutions, and ensures deployed agents deliver measurable workflow improvements while meeting governance, risk, and control standards for a regulated financial-services environment. The engineer works closely with the Senior Principal Architect for Agentic and MLOps Operations, business stakeholders, data and platform teams, and control partners as a founding member of a growing agentic AI engineering capability.

Requirements

  • Bachelor’s or Master’s degree in Computer Science, Engineering, or a related technical field, or equivalent practical experience.
  • At least 3 years of software engineering experience, including hands-on experience building AI/ML or LLM-based applications; production experience is preferred.
  • Strong proficiency in Python and experience building production-grade APIs, services, and integrations with enterprise systems.
  • Strong SQL and data engineering skills, including data profiling, quality validation, transformation, and pipeline development across structured and unstructured enterprise data sources.
  • Hands-on experience building agentic AI solutions, including LLM tool calling, retrieval-augmented generation (RAG), prompt engineering, and multi-step orchestration using frameworks such as LangGraph, Google ADK, or similar.
  • Solid working knowledge of Google Cloud Platform, particularly Vertex AI, Gemini models, and BigQuery, along with core GCP compute, storage, networking, and IAM services.
  • Experience designing LLM evaluation and testing approaches, including test datasets, accuracy and grounding metrics, regression testing, and guardrails against prompt injection and unsafe outputs.
  • Experience building auditable AI systems, including decision traceability, audit logging, lineage of data and model versions, and records of human approvals.
  • Experience with CI/CD, infrastructure-as-code (e.g., Terraform), containerization, observability, and cloud security practices such as identity federation, secrets management, and least-privilege access.
  • Strong communication skills, including the ability to work directly with business users through acceptance testing and document solutions for technical, risk, and governance audiences.

Nice To Haves

  • Experience with Microsoft Azure and Entra ID, and building on Microsoft 365 data (Exchange, Teams, SharePoint/OneDrive) via Microsoft Graph or Copilot extensibility.
  • Experience integrating AI solutions with enterprise SaaS and data sources such as Salesforce CRM, Marketo, master data management (MDM), and cloud-hosted or on-premises systems, including via Model Context Protocol (MCP) or API enablement of legacy systems.
  • Familiarity with TypeScript or Java for building integrations and services.
  • Experience delivering AI solutions in financial services or another regulated industry, including familiarity with model risk management, Responsible AI, data privacy, and investment management data.

Responsibilities

  • Design, build, and deliver production-grade agentic AI solutions, from prototype through deployment, to automate and enhance business workflows.
  • Assess data readiness by profiling, mapping, and validating source data; resolve quality and access gaps; and build pipelines, APIs, or semantic layers that make data and existing systems consumable by AI agents.
  • Develop agent logic, including prompts, retrieval, tool/API integrations, and orchestration, connecting agents to enterprise data sources and business applications.
  • Implement deterministic validation, guardrails, and human-in-the-loop approval steps to ensure AI outputs are accurate and safe for business decisions.
  • Build end-to-end auditability, capturing inputs, data sources, model versions, tool calls, outputs, and human approvals.
  • Produce documentation and evidence for governance, risk, compliance, and audit reviews.
  • Create test sets and evaluation pipelines to verify accuracy, grounding, reliability, and resilience against edge cases and adversarial inputs such as prompt injection.
  • Partner with business users during user acceptance testing, validate workflow improvements, and refine solutions based on feedback.
  • Deploy, monitor, and maintain solutions using CI/CD and infrastructure-as-code; track quality, latency, cost, and business outcome metrics; and troubleshoot, tune, and upgrade solutions in production.

Benefits

  • Retirement savings plan (401K) with company match.
  • Insurance coverage including basic life, medical, dental, vision, long-term disability, and optional additional coverages.
  • Paid time off, including vacation, sick leave, short-term disability, and family care responsibilities.
  • Access to the Employee Assistance Program.
  • Incentive compensation, including eligibility for annual performance-based awards, with certain sales-role exceptions.
  • Eligibility for certain tax-advantaged savings plans.
  • Inclusive development opportunities, flexible work-life support, paid volunteer days, and employee networks.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service