AI Applications Engineer

Edmund Optics•Barrington, NJ

5d•$91,000 - $120,000•Onsite

About The Position

Edmund Optics is hiring an AI Applications Engineer to build AI-powered business applications that connect AI models with company data, tools, APIs, and human review. The engineer will work directly with business stakeholders to understand workflows and translate business problems into working software, partnering with analytics, IT, cybersecurity, and continuous improvement teams to develop, deploy, and improve AI-driven solutions. The role owns scoped projects and is suited to an early-career engineer who has built AI applications and can translate AI capabilities into measurable business value. The position is based in Barrington, New Jersey. Initial work may include customer documentation workflows and demand forecasting applications. The engineer will evaluate application behavior and AI outputs, support reliable deployment within company policies and AI governance, and measure business results to improve solutions over time. Applicants are asked to include a brief description of an AI application they have built; a GitHub repository, portfolio, demo, or project write-up is welcome but optional.

Requirements

Demonstrated initiative and follow-through, including moving work forward independently and exercising judgment about when to clarify or escalate.
Experience building a working AI application that uses external tools or APIs, and ability to explain personal contributions, how tool calls are executed, and how results and failures are checked.
Ability to write, explain, debug, and test software in at least one relevant programming language.
Working knowledge of APIs, data structures, databases, and version control.
Working knowledge of agent tool/function calling, structured outputs, retrieval and context management, and agent orchestration, including how MCP clients and servers connect AI applications to tools and data.
Excellent communication skills and ability to understand business workflows and explain technical choices to non-technical stakeholders.
Demonstrated habit of learning and experimenting with emerging AI capabilities, applying feedback, and explaining what a new approach improves and where it falls short.
U.S. citizenship or permanent residence.
Ability to comply with federal, state, and company policies, procedures, and regulations.
Bachelor's degree in Computer Science or a related field.
Applicants must include a resume and a brief description of one AI application they built; relevant experience may come from employment, internships, research, coursework, or independent projects.

Nice To Haves

Experience with production deployment, monitoring, SQL, or business system integrations.
Hands-on experience building or integrating MCP servers or evaluating agent workflows.
Experience with forecasting or other applied data methods.
Experience with AI data platforms, especially Snowflake.
Exposure to optics, photonics, precision manufacturing, or a related technical industry.
Experience with cloud platforms, especially Microsoft Azure, including Azure OpenAI, Azure AI Foundry, or Azure Functions.
A GitHub repository, portfolio website, demo, or project write-up showcasing relevant work.

Responsibilities

Build applications that connect AI models with APIs, business data, and tools, including Model Context Protocol (MCP) servers and multi-step agent workflows.
Write, debug, test, and maintain application code and integrations, choosing an AI, analytical, or conventional software approach appropriate to each problem.
Meet with business stakeholders to understand workflows, clarify requirements, and agree on practical measures of success.
Identify useful next steps, build small working prototypes, and improve them through testing and feedback.
Evaluate application behavior and AI outputs, including missing information, incorrect answers, tool failures, and cases requiring human review.
Collaborate with IT, analytics, cybersecurity, continuous improvement, and business owners to deploy and support reliable applications within company policies and AI governance.
Surface blockers and possible next steps, communicate progress, document decisions, and address issues after launch.
Measure business results and improve solutions over time.
Stay current on AI models, agent frameworks, tool integrations, and development practices; test promising capabilities and recommend adoption based on usefulness, reliability, cost, and maintainability.