Sr Full Stack AI Engineer

Ameriprise Financial Services, LLC•Boston, MA

1d•$155,000 - $200,000•Hybrid

About The Position

Ameriprise is seeking a Senior AI Automation Engineer to mature and expand our enterprise AI Platform – AgentCore by designing, building, and scaling new AI-driven capabilities that directly support Portfolio Management and Research workflows. This role will serve as a hands-on technical leader responsible for operationalizing Anthropic Cloud Code and advanced Claude services (including Claude Interpreter) across Ameriprise—delivering secure, governed, and reusable AI components. The engineer will work closely with Portfolio Managers, Research Analysts, and Quant teams to translate high-value investment use cases into production-grade agentic solutions deployed on AgentCore AI (AgentCore) Platform Maturity Design agentic workflows and multi agent orchestration patterns using approved AgentCore frameworks and runtimes. Build AI capabilities that leverage: Tool calling Retrieval augmented generation (RAG) Structured data semantics Reusable prompt and skill Value Realization & Platform Adoption Demonstrate measurable impact on research productivity, decision velocity, and analytical depth. Support adoption via reference implementations, documentation, and enablement materials. Provide architectural guidance to teams building on AgentCore to prevent fragmentation and “shadow AI.”Enterprise Platform Enablement Integrate AI automation into existing enterprise platforms (e.g., CI/CD pipelines, SDLC tooling, cloud platforms). Establish reusable AI components, frameworks, and guardrails for product and engineering teams. Enable adoption through reference architectures, implementation patterns, and developer enablement. Value Realization & Measurement Identify and quantify productivity, quality, and cycle-time improvements driven by AI. Define KPIs and success metrics tied to SDLC efficiency, developer experience, and risk reduction. Support executive visibility into AI-driven outcomes and maturity progress. AI (AgentCore) Platform Maturity Design and build new AI capabilities, agents, and reusable skills on Ameriprise’s AgentCore platform, aligned with standard reference architectures, lifecycle management, and governance controls. Contribute to AgentCore core services including agent runtime integration, memory patterns, observability, versioning, and gated deployment models. Ensure all AI capabilities comply with Ameriprise security, auditability, cost attribution, and responsible AI standards. Anthropic & Claude Enablement Lead enterprise adoption of Anthropic Cloud Code, establishing: Cloud Code implementation patterns Prompt, tool, and skill composition standards Agent safety and policy enforcement mechanisms Claude Interpreter and higher-order reasoning services to enable: Data exploration and analysis Multi-step reasoning workflows Secure tool invocation within agent boundaries Investment & Research Use Case Delivery Partner directly with Portfolio Managers and Research Analysts to identify, design, and implement value-add AI use cases, such as: Research summarization and synthesis Scenario, factor, and exposure analysis Structured and unstructured data interpretation Investment insight acceleration Convert exploratory research into repeatable, production-ready AgentCore solutions.

Requirements

8+ years of experience in software engineering, automation, or platform engineering roles.
Proven hands-on experience implementing LLM based or agentic AI solutions in enterprise environments.
Demonstrated expertise with Anthropic Cloud Code and advanced Claude services (including interpreter style workflows).
Strong understanding of agent architectures, tool orchestration, and secure AI platform design.
Experience working with investment, research, or Portfolio Management business users.
Proficiency in Python and modern cloud native development patterns.
Experience building AI platforms or shared AI services in financial services or regulated environments.
Familiarity with portfolio management, investment research, or quantitative analytics workflows.
Experience integrating AI solutions with enterprise data platforms and analytics stacks.
Exposure to Responsible AI frameworks, model governance, and audit requirements.

Responsibilities

Design agentic workflows and multi agent orchestration patterns using approved AgentCore frameworks and runtimes.
Build AI capabilities that leverage: Tool calling, Retrieval augmented generation (RAG), Structured data semantics, Reusable prompt and skill.
Demonstrate measurable impact on research productivity, decision velocity, and analytical depth.
Support adoption via reference implementations, documentation, and enablement materials.
Provide architectural guidance to teams building on AgentCore to prevent fragmentation and “shadow AI.”
Integrate AI automation into existing enterprise platforms (e.g., CI/CD pipelines, SDLC tooling, cloud platforms).
Establish reusable AI components, frameworks, and guardrails for product and engineering teams.
Enable adoption through reference architectures, implementation patterns, and developer enablement.
Identify and quantify productivity, quality, and cycle-time improvements driven by AI.
Define KPIs and success metrics tied to SDLC efficiency, developer experience, and risk reduction.
Support executive visibility into AI-driven outcomes and maturity progress.
Design and build new AI capabilities, agents, and reusable skills on Ameriprise’s AgentCore platform, aligned with standard reference architectures, lifecycle management, and governance controls.
Contribute to AgentCore core services including agent runtime integration, memory patterns, observability, versioning, and gated deployment models.
Ensure all AI capabilities comply with Ameriprise security, auditability, cost attribution, and responsible AI standards.
Lead enterprise adoption of Anthropic Cloud Code, establishing: Cloud Code implementation patterns, Prompt, tool, and skill composition standards, Agent safety and policy enforcement mechanisms.
Enable Claude Interpreter and higher-order reasoning services to enable: Data exploration and analysis, Multi-step reasoning workflows, Secure tool invocation within agent boundaries.
Partner directly with Portfolio Managers and Research Analysts to identify, design, and implement value-add AI use cases, such as: Research summarization and synthesis, Scenario, factor, and exposure analysis, Structured and unstructured data interpretation, Investment insight acceleration.
Convert exploratory research into repeatable, production-ready AgentCore solutions.