AI Engineer - Backend & LLMs (Hybrid)

Kelly Services; Waltham (MA); Hybrid; USD 127,000 - 220,000; Full time

Benefits offered by this job

Medical Insurance

Dental Benefits

Vision Benefits

Flexible Paid Time Off (PTO)

401(k) Plan

Parental Leave

Life Insurance

Disability Coverage

Job summary

Kelly Services in the United States is hiring an AI Engineer, Agentic Customer Workflows to design and deploy backend AI features that power customer experiences. You will integrate LLMs into real-time services, own features end-to-end, and collaborate with product and engineering teams.

Ideal candidates have 4+ years of backend engineering plus hands-on experience deploying AI/LLM solutions, APIs, and microservices in production environments. This hybrid role is based in Waltham, MA.

Qualifications

• 4+ years backend software engineering experience (Python/Go/Java)
• 4+ years integrating ML or LLMs into production
• Experience building and maintaining APIs and microservices
• Strong distributed systems, cloud infra, observability
• Experience monitoring AI systems and quality frameworks

Responsibilities

• Design, build, and optimize backend services, APIs, and microservices supporting AI-powered workflows
• Integrate ML and LLM solutions into scalable production systems
• Own AI features from development to deployment, monitoring, and improvement
• Build evaluation frameworks to measure LLM quality and performance
• Troubleshoot AI services, model-serving infra, backend platforms
• Collaborate with cross-functional teams on architecture and planning
• Enhance scalability, reliability, observability, and performance

Skills

Python

Go/Java

LLM integration

APIs & microservices

Distributed systems

Observability

Communication

Team collaboration

Fast-paced environment

Tools

API development

Microservices

Real-time AI platforms

LLM deployment

Job description

Kelly Services in the United States is hiring an AI Engineer, Agentic Customer Workflows to design and deploy backend AI features that power customer experiences. You will integrate LLMs into real-time services, own features end-to-end, and collaborate with product and engineering teams.

Ideal candidates have 4+ years of backend engineering plus hands-on experience deploying AI/LLM solutions, APIs, and microservices in production environments. This hybrid role is based in Waltham, MA.