Software Engineer, AI Automation
New
J
JobgetherTechnology
United States; Alberta, British Columbia, or Ontario; other Canadian locations.Full-TimeMiddle
Salary115,600 - 160,600 USD per year
Apply NowOpens the employer's application page
Job Details
- Experience
- At least 5 years
- Required Skills
- PythonSQLGitCI/CD
Requirements
- At least 5 years of hands-on software development experience with demonstrated practical experience building and shipping production software.
- Substantial hands-on experience building applications powered by Large Language Models (LLMs), including prompting, tool use, agentic loops, and multi-step workflows.
- Shipped at least one AI agent or LLM-powered application that non-engineering users depend on in their day-to-day work.
- Understanding of the practical limitations and failure modes of LLM-based systems and how to design safeguards.
- Practical experience with agent tooling, including MCP, skill or tool authoring, and orchestrating agents against real systems of record.
- Experience building evaluation datasets and using evaluation results to make practical decisions about AI system quality.
- Fluent in Python and comfortable working with SQL and production data models.
- Experience using agentic coding tools such as Cursor.
- Understanding of core software delivery practices, including Git, continuous integration, containers, deployment, and production operations.
- Ability to work directly with non-technical business stakeholders to understand processes and translate needs into technical solutions.
Responsibilities
- Build and ship AI-powered applications that automate manual and repetitive business processes across multiple internal teams.
- Translate business processes, judgment calls, edge cases, and operational requirements into reusable skills that AI agents can reliably invoke.
- Design and implement agentic workflows that combine skills, tools, and systems of record into production-ready solutions.
- Connect agents to internal systems through Model Context Protocol (MCP) servers and expand MCP capabilities when required systems or data sources are not yet supported.
- Define success criteria and establish evaluation standards with business stakeholders before building or deploying AI solutions.
- Take AI agents from proof of concept through production deployment, including permissions, human-in-the-loop checkpoints, audit trails, and rollback mechanisms.
- Monitor and improve agent behavior based on real-world usage, identifying failure modes and implementing appropriate safeguards.
View Full Description & ApplyYou'll be redirected to the employer's site
