AI ENGINEER

MGI Inc. is hiring an AI Engineer to help build and expand our internal AI automation platform. This is not an exploratory or research position. We have a working production system in daily use across our project management, accounting, contracting, and IT departments, and we are looking for an experienced engineer to help extend it, harden it, and bring new departments online. You will design, build, and maintain AI agents that perform real work: answering employee questions from live company data, generating documents, monitoring systems, analyzing bids, and automating recurring workflows. Some agents serve general employee needs, and others are purpose-built for a single specialized task. You will create and maintain systems end to end, from the API integration through to the deployed agent that employees rely on every day.

WHAT YOU WILL WORK WITH

Our platform is substantial and already in production:- A multi-agent system with several named AI agents, each with its own role, tool set, and company identity, serving different departments- Roughly 200,000 lines of Python powering agent tools and integrations- Chat-based agents that employees message directly in Microsoft Teams and receive substantive answers from- A retrieval system holding millions of indexed documents, including company email and attachments, construction codes and standards, regulations, and project documentation- Deep third-party integrations including Procore, Microsoft 365 and Graph API, SharePoint, payroll and accounting systems, contracting data sources, and security tooling- Well over a hundred scheduled automation jobs handling syncs, monitoring, reporting, and alerting- A local compute fleet running vector search, model routing, and local inference alongside frontier API modelsThe platform layer is OpenClaw. Agent behavior is defined through configuration and markdown, with Python implementing the tools each agent can call.

Responsibilities

• Design, develop, and refine AI models using frameworks such as TensorFlow and other machine learning tools to solve complex problems.
• Implement natural language processing (NLP) techniques for data extraction and analysis from unstructured data sources.
• Utilize big data systems like Hadoop and Spark to process large datasets efficiently for predictive modeling analysis.
• Collaborate with cross-functional teams to integrate AI models into cloud-based platforms utilizing AWS and machine learning cloud services.
• Conduct statistical analysis, model training, evaluation, and validation to ensure high accuracy and robustness of AI solutions.
• Develop scalable data pipelines using ETL processes, Talend, and SQL databases to support ongoing AI initiatives.
• Deploy AI models into production environments with a focus on model evaluation, monitoring, and continuous improvement.

OpenClaw or comparable agent framework. Hands-on experience building agents is required. You should be comfortable with agents and session management, the skills system, tool definitions and tool permission policy, gateway configuration, scheduled agent tasks, agent memory and context files, and sub-agent orchestration

Production LLM engineering. You have built and shipped LLM-powered systems that other people depended on, including:

• Tool and function calling, and designing tool interfaces a model can use reliably
• Multi-step agentic workflows with planning, tool selection, and error recovery
• Context management: deciding what belongs in the context window versus retrieval, and managing the associated cost and latency tradeoffs
• Retrieval-augmented generation, including chunking strategy, embedding selection, hybrid search, reranking, and honest evaluation of retrieval quality
• Structured output generation and schema validation-
• Model selection and routing across cost, latency, and capability tradeoffsStrong
• Strong Python skills. You can work confidently in a large existing codebase: reading unfamiliar code, tracing bugs across modules, writing tests, and refactoring safely.
• API integration experience. Much of this work is systems integration rather than model work. You need real proficiency with REST APIs, OAuth 2.0 and token management, rate limiting, retries, pagination, and idempotency. Critically, you should be someone who verifies API behavior empirically rather than assuming the documentation is complete or current.
• Diagnostic judgment. The hardest problems in this role fail silently rather than loudly: a monitor that reports healthy because it quietly stopped checking, an agent answering confidently from stale data, or a data feed that looks like a slow week but is actually broken. We need an engineer whose instinct is to ask how they know something is genuinely working, and then go prove it.

PREFERRED QUALIFICATIONS

Microsoft 365 and Graph API: mail, calendar, Teams, SharePoint, app registrations, and permission scopes

Vector databases in production, ideally Qdrant, and practical experience with embedding models

Local model hosting and serving: Ollama, vLLM, LiteLLM, and quantization tradeoffs- Mesh networking such as Tailscale, and basic reverse proxy configuration

PowerShell and Windows endpoint scripting- Evaluation frameworks for measuring LLM output quality

Front-end skills for internal dashboards and portals

Vision and OCR work for drawing analysis and scanned document extraction

$75,000 - $85,000 - Compensation is commensurate with experience and will be discussed during the interview process. This is a full-time position based in Boise, Idaho, with hybrid flexibility possible.MGI Inc. is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or protected veteran status.

Join us in shaping the future of healthcare technology by leveraging cutting-edge AI innovations that make a real difference in patient safety!

Pay: $75,000.00 - $85,000.00 per year

Benefits:

• Dental insurance
• Health insurance
• Paid time off
• Vision insurance

MGI Inc. contractor working primarily on federal healthcare construction projects. We are a Service-Disabled Veteran-Owned Small Business and a repeat Inc. 5000 honoree. We are investing heavily in AI automation so our staff can focus on judgment, relationships, and skilled work rather than repetitive administrative tasks.