> Markdown version of [/jobs/ext/4313644-ai-engineer-hybrid](https://www.wearedevelopers.com/jobs/ext/4313644-ai-engineer-hybrid). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# AI Engineer (Hybrid)

- **Company:** Kelly Services Inc.
- **Location:** Boston, MA, United States
- **Experience:** Experienced
- **Salary:** $293,280.0
- **Contract:** Permanent contract
- **Skills:** LangGraph Framework, Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Automation of Tests, Continuous Integration, Information Engineering, Software Debugging, Python (Programming Language), Machine Learning, Regression Testing, Software Engineering, Systems Integration, Enterprise Software Applications, Large Language Models, Prompt Engineering, Generative AI, Backend, Agentic-AI, Containerization, AI Platforms, Information Technology, Amazon Bedrock, Api Design, Software Version Control
- **Published:** October 26, 2026
- **Apply:** https://dejobs.org/x/x/8AE6FF2B10EE4F379F86EC9C1B6462CF/job/

## About the Role

· Bachelor's degree in Computer Science, Engineering, or related quantitative field with 7+ years of software engineering, machine learning, or data engineering experience, or Master's degree with 5+ years of relevant experience

· 2+ years of hands-on experience building LLM-based applications, including at least one production-deployed agentic system used by real users

· Strong Python development experience and software engineering fundamentals

· Experience building APIs, integrating tools and services, automated testing, version control, debugging, and error handling

· Hands-on experience with agent frameworks or SDKs, with LangGraph strongly preferred

· Experience using major model APIs or managed AI platforms such as Amazon Bedrock

· Experience building production AI agents that integrate with enterprise systems, APIs, and tools

· Experience evaluating LLM applications and agents using test datasets, metrics, regression testing, and model-based evaluators

· Understanding of AI agent reliability, security risks, governance requirements, and responsible AI practices

· Strong communication skills and the ability to explain AI behaviors and limitations to technical and non-technical stakeholders

· Proven ability to solve complex, ambiguous problems independently and deliver results

Desired Skills & Experience

· Insurance industry experience preferred

· Claims or underwriting expertise strongly preferred

· Experience deploying AI applications to AWS cloud environments

· Experience with containerization and CI/CD pipelines

· Experience with retrieval-augmented generation (RAG), context engineering, and structured outputs

· Experience integrating agents with enterprise systems through APIs and MCP servers

· Experience mentoring team members and establishing engineering best practices across teams

What You Will Be Doing

Tech Breakdown

· Designing, building, and deploying AI agents and multi-step agentic workflows

· Developing Python-based backend services, APIs, and enterprise integrations

## Description

· Implementing cloud-native AI solutions using AWS, containers, and CI/CD practices

· Building evaluation frameworks, observability, monitoring, and governance controls

· Integrating AI agents with enterprise systems, data sources, APIs, and MCP services

Daily Responsibilities

· Design and deliver agentic AI solutions that improve underwriting, claims, and other insurance workflows

· Translate solution designs into production-ready AI services and applications

· Build secure, resilient backend services with testing, monitoring, and audit capabilities

· Create evaluation datasets, automate testing, and continuously improve agent performance

· Implement guardrails, human-in-the-loop workflows, and governance controls

· Collaborate with architects, product owners, business stakeholders, and technical teams to prototype, deploy, and scale AI solutions

· Measure technical performance and business value while communicating outcomes and limitations to stakeholder