MGI Inc. is building and expanding an internal AI automation platform that powers production AI agents used across project management, accounting, contracting, and IT. This hybrid role in Meridian, ID focuses on designing agents that do real end-to-end work, from API integration through deployed solutions employees message and rely on in daily operations.
You’ll work with a multi-agent system where each named agent has its own identity, tool set, and department use cases. The platform layer is OpenClaw, with agent behavior defined through configuration and markdown, while Python implements the tools each agent can call. The environment also includes a retrieval system indexing millions of documents, plus deep third-party integrations that connect the agents to business systems.
What you’ll do
- Design, develop, and refine AI models using TensorFlow and other machine learning tools to address complex problems.
- Apply NLP techniques for data extraction and analysis from unstructured sources.
- Use Hadoop and Spark to process large datasets for predictive modeling analysis.
- Collaborate cross-functionally to integrate models into cloud-based platforms leveraging AWS and machine learning cloud services.
- Perform statistical analysis, model training, evaluation, and validation to ensure accuracy and robustness.
- Build scalable ETL data pipelines using Talend and SQL databases to support ongoing AI initiatives.
- Deploy models to production with an emphasis on model evaluation, monitoring, and continuous improvement.
Agent and integration responsibilities
- Work in an OpenClaw agent environment, including agent memory and context files, scheduled tasks, tool definitions and tool permission policy, gateway configuration, and sub-agent orchestration.
- Implement reliable tool and function calling with tool interfaces designed for dependable use by the model.
- Build multi-step agentic workflows with planning, tool selection, and error recovery.
- Handle context management decisions, including what belongs in the context window versus retrieval, with attention to cost and latency tradeoffs.
- Develop retrieval-augmented generation (RAG) pipelines: chunking strategy, embedding selection, hybrid search, reranking, and honest evaluation of retrieval quality.
- Create structured outputs with schema validation.
- Manage model selection and routing across cost, latency, and capability tradeoffs, including local inference alongside frontier API models.
Requirements
- OpenClaw or comparable agent framework, plus hands-on experience building agents.
- Comfort 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.
- Experience with tool and function calling and designing tool interfaces that a model can use reliably.
- Ability to build multi-step agentic workflows including planning, tool selection, and error recovery.
- Strong context management skills for context window versus retrieval decisions, including cost and latency tradeoffs.
- RAG experience: chunking strategy, embedding selection, hybrid search, reranking, and evaluation of retrieval quality.
- Experience generating structured output with schema validation.
- Experience with model selection and routing across cost, latency, and capability tradeoffs.
- Strong Python skills for working safely in a large existing codebase: reading unfamiliar code, tracing bugs across modules, writing tests, and refactoring.
- API integration experience focused on systems integration: REST APIs, OAuth 2.0 and token management, rate limiting, retries, pagination, and idempotency.
- Diagnostic judgment for issues that fail silently, including verifying monitoring health and confirming data freshness.
Benefits
- Dental insurance
- Health insurance
- Paid time off
- Vision insurance
Compensation: $75,000 - $85,000 per year (commensurate with experience and discussed during the interview process).
Work location: In person with hybrid flexibility possible. MGI Inc. is an equal opportunity employer, and all qualified applicants receive consideration without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or protected veteran status.
