AI Engineer

Allspring Global Investments Holdings, LLC•Charlotte, NC

5d•Hybrid

About The Position

Reporting into Engineering & Technology and working day-to-day with the AI Solutions Architect & Technical Lead, this role is a hands-on engineer responsible for implementing, testing, and supporting production-ready generative AI applications—especially agentic workflows—based on established enterprise architecture standards and guardrails. The AI Engineer builds the workflows, integrations, orchestration logic, and supporting services that enable large language models to interact with enterprise data, internal systems, and business processes in secure, reliable, and maintainable ways. We currently operate in a hybrid working model, whereby you will be required to work in-office 4 days per week. Location(s): Milwaukee, WI or Charlotte, NC

Requirements

Bachelor’s degree in Computer Science, Engineering, or related field, or equivalent practical experience.
1–3 years of professional software engineering experience (or equivalent internships/co-ops/project work), with some hands-on exposure to AI/ML or LLM-based applications.
Strong programming skills in Python and experience building backend services and API integrations.
Experience consuming LLM services via APIs/SDKs and working with at least one common LLM framework or orchestration library Exposure to generative AI application development using common LLM patterns (prompting, retrieval, structured outputs, evaluation, and workflow orchestration).
Experience building and deploying applications in AWS (or similar cloud), including familiarity with IAM, networking basics, and managed services.
Strong understanding of software engineering fundamentals, including testing, version control, CI/CD, debugging, and secure development practices.
Ability to operate effectively in a regulated environment with strong attention to quality, traceability, and control requirements.
Familiarity with financial services, asset management, or document-intensive business processes.

Nice To Haves

Experience with Amazon Bedrock, AWS SDKs, Lambda, Step Functions, or related AWS-native AI implementation patterns.
Interest in (or early experience with) agentic systems, multi-step workflows, and tool-calling patterns.
Familiarity with knowledge bases, vector search, retrieval pipelines, and AI output evaluation methods.
Experience supporting use cases in investments, compliance, marketing, operations, client servicing, or RFP-related functions.

Responsibilities

Implement and support generative AI applications and agentic workflows for enterprise and business platforms, following approved reference architectures and standards.
Build orchestration logic for multi-step tasks (tool usage, API calls, retrieval workflows, approvals/human-in-the-loop steps) as designed by the AI Solutions Architect & Technical Lead.
Develop and maintain integrations between AI services and internal systems, structured/unstructured data sources, and approved enterprise or third-party APIs.
Implement prompt pipelines, structured output handling, evaluations, and automated tests to improve quality, reliability, and auditability.
Instrument solutions for observability (logging/metrics/tracing) and collaborate on performance and cost optimization.
Translate solution designs into working code by implementing components, services, and pipelines aligned to security, compliance, and governance guardrails.
Support user testing and iteration by partnering with product and business stakeholders to refine agent behavior, output quality, and user experience.
Create and maintain technical documentation (runbooks, integration notes, test plans, and deployment steps) to support reliable delivery and operations.
Troubleshoot and remediate production issues related to model outputs, grounding/retrieval, orchestration behavior, or API interactions.
Contribute reusable components and templates (connectors, evaluators, agent scaffolding) and follow established corporate coding standards and review practices.
Participate in code reviews and technical learning, incorporating feedback from senior engineers to improve engineering quality and delivery speed.