AI Engineer

Alight; Deerfield (IL); Hybrid; USD 120,000 - 190,000; Full time

Benefits offered by this job

Health, dental, vision

Wellbeing programs

Retirement plans

Generous time off

Parental leave

Continuing education

Career growth

Job summary

Alight is building an AI engineering platform to support AI delivery across the organization. In this role, you will ship agentic experiences with guardrails, retrieval, and operational controls.

You will engineer patterns, MCP servers, and LangGraph architectures to enable safe multi-agent collaboration. The position focuses on hands-on building, CI/CD automation for AI agents on AWS, and production observability with OpenTelemetry.

Qualifications

• Proficiency in Python 3.10+.
• Experience with AWS IAM, ECS, Fargate and networking.
• Strong software engineering discipline: version control, code review, testing, documentation, and security awareness.

Responsibilities

• Build agent patterns, guardrails for assistant experiences.
• Develop MCP server for a skills registry inside the IDE.
• Create reusable LangGraph architectures with memory, multi-agent orchestration, and tool-use safety.

Skills

Python

AWS

Software engineering

Git/GitHub

Testing

Documentation

Security awareness

Tools

Terraform

OpenTelemetry

Job description

Alight is building an AI engineering platform to support AI delivery across the organization. As an AI Engineer, you will help production teams ship agentic experiences with strong retrieval, evaluation, and operational controls. This is a hands‑on role focused on building the patterns, infrastructure, and tooling that keep AI systems reliable and measurable.

What you’ll build

• Agent patterns, retrieval, and guardrails for assistant experiences that answer participant questions and can carry out transactions on their behalf
• A dedicated MCP server that provides a skills registry for AI coding agents directly inside the IDE
• Reusable agent architectures in LangGraph, including multi‑agent orchestration, memory, and tool‑use safety with guardrails
• An agent evaluation platform using frameworks such as DeepEval and Ragas, with quality gates that prevent poor deployments in CI/CD
• Document ingestion and retrieval pipelines covering chunking, embedding, vector search, reranking, and citations
• CI/CD and deployment automation for AI agents on AWS, including ECS, Fargate, and Agent Core
• AI-enabled devcontainers with built‑in tooling, validation, and testing
• Production observability with OpenTelemetry, including dashboards plus LLM cost and token tracking
• Governance controls implemented as automated pipeline checks with evidence collected automatically
• Scalability features such as semantic caching, rate limiting, and graceful degradation under load
• Reference implementations, along with SDK and CLI tooling, and documentation that other engineers rely on

Core requirements

• Python (3.10+) as the primary language for the team
• AWS working knowledge of key services such as IAM, ECS/Fargate, and networking, plus comfort in cloud‑native environments
• Software engineering discipline, including version control (Git/GitHub), code review, testing, documentation, and clean code
• Security awareness, with attention to secrets, permissions, and data protection for systems handling sensitive information

Where your expertise fits

• AI agent development: LangGraph or similar, multi‑agent orchestration, memory, tool use, guardrails, prompt and workflow design
• Data and retrieval engineering: chunking, embeddings and vector search, RAG, hybrid search, reranking, retrieval evaluation
• Quality and evaluation: DeepEval and Ragas, CI/CD quality gates, groundedness and safety metrics, test automation
• Platform and infrastructure: CI/CD, Terraform, AWS container orchestration (ECS, Fargate), secrets and IAM, progressive deployment
• Observability and operations: OpenTelemetry tracing, dashboards and alerting, LLM cost and token tracking, feedback loops
• Developer experience: MCP servers, devcontainers, CLI and SDK tooling, prompt libraries, documentation, and reference implementations

Benefits and support

• Health, dental, and vision coverage starting Day One
• Wellbeing programs
• Retirement plans with contribution matching
• Generous time off
• Parental leave
• Continuing education
• Career growth opportunities

Flexible work and recognition

Alight considers flexible working arrangements wherever possible. The company has been a leader in flexible workspace and has been recognized as a “Top 100 Company for Remote Jobs” for 6 years in a row.

Alight has received multiple awards, including “Great Place to Work” for the past 7 years and Fortune’s “Best Companies to Work For”.

Work location

Deerfield, IL (remote)

Interview and hiring notes

• Background checks may include SSN/SIN validation, education verification, employment verification, and criminal checks, plus searches against global sanctions and government watch lists, credit check, and/or drug test depending on the role.
• Virtual interviews must be conducted on video.
• Alight is a camera‑on culture and may require occasional travel to one of its physical office locations.

Inclusion and accommodations

Alight will provide reasonable accommodations for candidates with disabilities during the hiring process. If you need accommodation, contact [e-mail].

Authorization to work

Applicants must have work authorization for the employing country that does not, now or in the future, require visa sponsorship for employment authorization with Alight.

Note: This job description does not restrict management’s right to reassign duties and responsibilities to other entities, including subsidiaries, partners, or purchasers of Alight business units.