Junior AI Engineer

UniFirst•Wilmington, MA

About The Position

We are looking for an early-career Junior AI Engineer to help build, test, monitor, optimize, and document enterprise-grade AI solutions using Microsoft Azure AI Services. Reporting to the AI Engineer, you will contribute to backend services, autonomous agents, retrieval systems, and client-facing tools that support the organization’s next generation of intelligent applications. This role emphasizes hands-on engineering, structured evaluation, operational monitoring, performance and cost optimization, and reusable technical guidance. You will work closely with AI, software, architecture, and infrastructure teams while developing broader ownership of defined AI components and operational processes.

Requirements

0-2 years of relevant software development experience through professional work, internships, academic projects, or personal projects using Python, C#, JavaScript, or Java.
Experience or demonstrated familiarity with one or more Azure AI services, such as Azure OpenAI, Cognitive Services, Azure AI Search, Azure Machine Learning, or Azure Functions.
Familiarity with software testing concepts, including unit, integration, regression, and automated testing.
Ability to use metrics and structured evaluations to compare AI model, prompt, or retrieval performance.
Familiarity with application monitoring, logging, telemetry, dashboards, and operational troubleshooting.
Ability to analyze tradeoffs among response quality, reliability, latency, token usage, and cost.
Strong research, technical writing, collaboration, problem-solving, and communication skills.

Nice To Haves

Experience orchestrating RAG pipelines or combining structured and unstructured data in AI workflows.
Exposure to LLM evaluation frameworks, AI observability platforms, prompt testing tools, or custom evaluation pipelines.
Experience experimenting with multiple language models, embedding models, rerankers, prompts, or retrieval configurations.
Familiarity with Azure Data Lake, Blob Storage, document intelligence, or enterprise-scale datasets.
Experience developing simple client-side applications using React, Streamlit, or JavaScript.
Familiarity with MLOps practices and model lifecycle management.
Familiarity with Confluence, Cursor rules, repository-level instructions, or similar engineering knowledge-management practices.
Understanding of enterprise architecture, IT compliance, responsible AI, and production deployment patterns.
Relevant coursework, internships, certifications, or project experience in artificial intelligence, machine learning, data engineering, or software engineering.
Microsoft Azure certifications, such as Azure AI Engineer Associate (AI-102) or Azure Data Scientist Associate (DP-100).

Responsibilities

Set up and configure AI-powered services using Azure OpenAI, Cognitive Services, Azure AI Search, Azure Machine Learning, and Azure Functions.
Develop and maintain automated test suites for AI systems, including prompt regression, retrieval-quality, response-quality, safety, and end-to-end integration tests.
Create reusable evaluation datasets, test cases, scorecards, and performance baselines for AI applications and components.
Set up and maintain monitoring for response quality, failures, latency, token usage, model cost, retrieval performance, and other operational metrics.
Run structured experiments across models, prompts, retrieval settings, and search parameters to maintain quality while reducing token usage, latency, and operating cost.
Configure and optimize Azure AI Search, including semantic ranker, hybrid retrieval, vector search, filters, scoring profiles, top-k settings, chunking strategies, and reranking approaches.
Evaluate alternative language, embedding, and reranking models using documented benchmarks and recommend appropriate options for defined use cases.
Create backend components and lightweight client-side tools that expose AI capabilities across business systems.
Research emerging AI engineering practices, tools, frameworks, and vendor guidance, and translate findings into actionable recommendations.
Partner with engineers and architects to document approved AI patterns, implementation guidance, troubleshooting procedures, and best practices in Confluence.
Maintain developer-focused versions of AI guidance as Cursor rules, repository instructions, templates, and reusable examples, keeping them synchronized with enterprise documentation.
Collaborate with AI engineers, enterprise architects, developers, infrastructure teams, and business partners to deliver secure, governed, and responsible AI solutions.