Senior Software Engineer, AI Automation - Coalition

About Coalition

Coalition is the world's first Active Insurance provider designed to help prevent digital risk before it strikes. Founded in 2017, Coalition combines comprehensive insurance coverage and innovative cybersecurity tools to help businesses manage and mitigate potential cyberattacks.

Opportunities to make an impact with bold thinking are real—and happening daily at Coalition.

About the Role

Coalition is building an AI Automation team to eliminate manual work and improve how teams across the company operate. As a Senior Software Engineer, AI Automation, you will lead the design and delivery of reliable, production-grade AI agents and workflows that solve meaningful business problems.

This is a senior individual-contributor role for an AI-native engineer who can move from ambiguous business problems to durable technical solutions. You will work closely with internal operators, product and data partners, and engineering teams to understand complex processes, develop reusable agent capabilities, and establish the technical patterns that allow AI automation to scale safely across Coalition.

You will balance rapid experimentation with strong engineering judgment. You will define system architecture, establish evaluation and reliability practices, and ensure that production agents operate with the appropriate controls for permissions, auditability, human review, and rollback.

Key Responsibilities

• Lead the technical design and delivery of AI agents, reusable skills, and automation workflows used by Coalition’s internal teams.
• Translate complex, ambiguous business processes, judgment calls, and edge cases into reliable, maintainable software.
• Design and evolve integrations between agents and systems of record using MCP and comparable tool-integration frameworks.
• Define architecture, interfaces, data contracts, and operational standards for production AI systems.
• Establish evaluation strategies, quality baselines, and release criteria; use results to make sound deployment and iteration decisions.
• Build systems with robust controls for permissions, observability, auditability, human-in-the-loop review, failure containment, and rollback.
• Partner with data engineering and business stakeholders to ensure automations use trustworthy data and have sustainable ownership.
• Drive technical decisions across multiple workflows, identify reusable patterns, and raise the engineering bar for the team.
• Mentor engineers and technical partners through design reviews, implementation guidance, and practical AI engineering standards.
• Document systems, decisions, and operating practices so that teams can safely maintain and extend what you build.

Skills and Qualifications

• 7+ years of hands-on software engineering experience, including substantial recent experience building and shipping LLM-backed applications used by real users.
• Demonstrated experience taking AI agents or multi-step automation workflows from prototype through reliable production operation.
• Strong Python engineering skills and practical SQL expertise, including the ability to work directly with production data models.
• Deep experience with prompting, tool use, agentic loops, structured outputs, multi-step workflows, error handling, and production deployment.
• Experience designing and operating systems that integrate with business-critical systems of record.
• Strong judgment around evaluation methodology, reliability, safety controls, and the tradeoffs required to deploy AI systems responsibly.
• Solid production engineering fundamentals across Git, CI/CD, containers, deployment, monitoring, testing, permissions, and rollback.
• Ability to lead technical work in ambiguous environments, influence stakeholders, and turn incomplete requirements into practical, high-quality solutions.
• Clear written and verbal communication skills, with the ability to work directly with both technical and non-technical partners.

Bonus Points

• Experience building or maintaining MCP servers, agent platforms, or reusable tool/skill frameworks.
• Experience designing evaluation harnesses, test datasets, and monitoring for LLM-backed systems.
• Background in internal tools, solutions engineering, professional services, startup environments, or founding teams.
• Familiarity with systems such as Linear, Jira, Zendesk, Salesforce, or Snowflake.
• Experience in insurance, fintech, cybersecurity, or another regulated environment where correctness, traceability, and controls have meaningful business impact.
• Experience mentoring engineers or acting as a technical lead for complex cross-functional initiatives.

Compensation & Benefits

• Base Salary Range: $134,600 CAD – $199,600 CAD (depending on geographic location in Canada)
• 100% medical, dental, and vision coverage
• Flexible PTO
• Annual home office stipend and WeWork access
• Mental & physical health wellness programs (Headspace, Lumino, etc.)
• Competitive compensation and opportunity for advancement