Senior AI/ML Engineer

Vizient, Inc.; Chicago (IL); On-site; USD 102,000 - 179,000; Full time

Benefits offered by this job

Incentive eligible

Benefits package

Job summary

Vizient, Inc. in Chicago is seeking an experienced AI engineer to design, build, deploy, and support production AI capabilities for complex enterprise workflows.

You will develop AI-enabled applications using large language models, retrieval, structured data, and deterministic processing, collaborating with domain experts, data teams, and software engineers to deliver maintainable, observable solutions. The role emphasizes evaluation, testing, observability, security, and cost considerations,

Qualifications

• 5 or more years of relevant experience required.
• Strong experience developing production applications using Python.
• Hands-on experience building, deploying, and supporting generative AI or machine learning applications in production environments.
• Experience integrating commercial or open-source large language models through APIs or managed AI platforms.
• Experience with prompt engineering, structured model outputs, tool or function calling, retrieval-augmented generation, or agentic workflows.
• Experience building data-driven APIs and distributed application services using FastAPI or comparable frameworks.
• Experience developing automated tests and evaluation methods for nondeterministic AI behavior.
• Experience with embeddings, semantic search, vector retrieval, reranking, or comparable knowledge-retrieval techniques.
• Experience with cloud-native development, CI/CD pipelines, containerized services, and production deployment.
• Experience debugging complex issues across application code, enterprise data, AI models, retrieval systems, and distributed workflows.
• Experience with Microsoft Azure, Azure AI Foundry, Azure AI Search, Databricks, or Azure Service Bus preferred.
• Experience with AI evaluation, tracing, observability tooling, SQL, NoSQL databases, or agent‑orchestration frameworks preferred.
• Experience developing applications involving sensitive, regulated, or high‑consequence enterprise data preferred.

Responsibilities

• Design and implement production AI-enabled application services and workflow components.
• Build modular large language model and agentic capabilities with clearly defined responsibilities, inputs, outputs, and evaluation criteria.
• Develop retrieval and grounding solutions using structured data, semantic search, vector retrieval, and enterprise knowledge sources.
• Combine deterministic processing, business rules, retrieval, and model-based inference appropriately within application workflows.
• Build APIs, services, orchestration components, and asynchronous processing capabilities for production AI workloads.
• Develop automated evaluation and regression testing for large language model and AI behavior.
• Instrument applications to trace inputs, intermediate results, model interactions, decisions, errors, latency, and operational behavior.
• Investigate AI failure modes and use evaluation evidence to improve prompts, retrieval, workflow design, model selection, and application logic.
• Evaluate models and implementation approaches based on measurable quality, performance, security, maintainability, and cost.
• Implement controls that validate, constrain, and monitor model outputs within enterprise applications.
• Collaborate with domain experts to translate complex decision processes into maintainable software behavior.
• Participate in architecture reviews, technical design sessions, code reviews, and continuous improvement activities.
• Develop reusable AI engineering patterns, components, documentation, and evaluation practices.
• Support deployed AI applications through monitoring, troubleshooting, performance optimization, and production issue resolution.

Skills

Python

Production AI

APIs

FastAPI

CI/CD

Observability

Debugging

Embeddings

Semantic search

Vector retrieval

Agentic workflows

Prompt engineering

Education

Relevant degree preferred

Tools

Azure

Azure AI Foundry

Azure AI Search

Databricks

Azure Service Bus

Terraform

Job description

When you're the best, we're the best. We instill an environment where employees feel engaged, satisfied and able to contribute their unique skills and talents while living and working as their authentic selves. We provide extensive opportunities for personal and professional development, building both employee competence and organizational capability to fuel exceptional performance through an inclusive environment both now and in the future.

Summary:

In this role, you will design, build, deploy, and support production AI capabilities for complex enterprise workflows. You will develop AI-enabled applications that combine large language models, retrieval, structured and unstructured data, deterministic processing, APIs, and distributed services to produce reliable and explainable results. You will partner with domain experts, architects, data teams, and software engineers to translate specialized knowledge into maintainable solutions while establishing the evaluation, testing, and observability practices needed to operate AI applications within measurable quality boundaries.

Responsibilities:

• Design and implement production AI-enabled application services and workflow components.
• Build modular large language model and agentic capabilities with clearly defined responsibilities, inputs, outputs, and evaluation criteria.
• Develop retrieval and grounding solutions using structured data, semantic search, vector retrieval, and enterprise knowledge sources.
• Combine deterministic processing, business rules, retrieval, and model-based inference appropriately within application workflows.
• Build APIs, services, orchestration components, and asynchronous processing capabilities for production AI workloads.
• Develop automated evaluation and regression testing for large language model and AI behavior.
• Instrument applications to trace inputs, intermediate results, model interactions, decisions, errors, latency, and operational behavior.
• Investigate AI failure modes and use evaluation evidence to improve prompts, retrieval, workflow design, model selection, and application logic.
• Evaluate models and implementation approaches based on measurable quality, performance, security, maintainability, and cost.
• Implement controls that validate, constrain, and monitor model outputs within enterprise applications.
• Collaborate with domain experts to translate complex decision processes into maintainable software behavior.
• Participate in architecture reviews, technical design sessions, code reviews, and continuous improvement activities.
• Develop reusable AI engineering patterns, components, documentation, and evaluation practices.
• Support deployed AI applications through monitoring, troubleshooting, performance optimization, and production issue resolution.

Qualifications:

• Relevant degree preferred.
• 5 or more years of relevant experience required.
• Strong experience developing production applications using Python.
• Hands-on experience building, deploying, and supporting generative AI or machine learning applications in production environments.
• Experience integrating commercial or open-source large language models through APIs or managed AI platforms.
• Experience with prompt engineering, structured model outputs, tool or function calling, retrieval-augmented generation, or agentic workflows.
• Experience building data-driven APIs and distributed application services using FastAPI or comparable frameworks.
• Experience developing automated tests and evaluation methods for nondeterministic AI behavior.
• Experience with embeddings, semantic search, vector retrieval, reranking, or comparable knowledge-retrieval techniques.
• Experience with cloud-native development, CI/CD pipelines, containerized services, and production deployment.
• Experience debugging complex issues across application code, enterprise data, AI models, retrieval systems, and distributed workflows.
• Experience with Microsoft Azure, Azure AI Foundry, Azure AI Search, Databricks, or Azure Service Bus preferred.
• Experience with AI evaluation, tracing, observability tooling, SQL, NoSQL databases, or agent‑orchestration frameworks preferred.
• Experience developing applications involving sensitive, regulated, or high‑consequence enterprise data preferred.

Estimated Hiring Range:

At Vizient, we consider skills, experience, and organizational needs in our compensation approach. Geographic factors may adjust the range estimate and hires typically fall below the top range. Compensation decisions are tailored to individual circumstances. The current salary range for this role is $102,400.00 to $179,000.00.

This position is also incentive eligible.

Vizient has a comprehensive benefits plan! Please view our benefits here:

http://www.vizientinc.com/about-us/careers

Equal Opportunity Employer: Females/Minorities/Veterans/Individuals with Disabilities

The Company is committed to equal employment opportunity to all employees and applicants without regard to race, religion, color, gender identity, ethnicity, age, national origin, sexual orientation, disability status, veteran status or any other category protected by applicable law.