AI Solutions Engineer

Role overview

Building and operating AI solutions

• Assess how work is performed and prioritize changes that remove steps, reduce errors, and reach more people.
• Design, build, and ship AI solutions from prototype through production for sales, community teams, accounting, and marketing.
• Integrate with HubSpot, Microsoft 365, Snowflake, property management and finance platforms, and vendor APIs.
• Build on analytics-owned governed data models and semantic layers; communicate agent data needs.
• Maintain reusable patterns, prompts, tools, and evaluation sets.
• Own production evaluation, monitoring, exception handling, escalation, and model costs.
• Keep human review for consequential actions; ship through source control and pull requests and document support needs.
• Maintain an inventory of agents, prompts, integrations, ownership, and access.
• Partner with business leaders to define success, verify value, observe adoption, iterate, and train users.

Engineering requirements

• 5+ years shipping and supporting software used by real users.
• Strong Python and SQL; backend engineering is central. A second language such as TypeScript, Node.js, or Go is welcome.
• Frontend ability to deliver usable interfaces with React and TypeScript, Streamlit, Power Apps, or embedded experiences.
• Experience with REST APIs, webhooks, event-driven integrations, retries, idempotency, and failure handling.
• Relational data and data modeling knowledge, plus working knowledge of document or vector stores and caching.
• Experience with CI/CD, pull-request development, automated testing, and infrastructure as code; Azure is used, while AWS or Google Cloud experience transfers.
• Daily use of AI coding tools such as Claude Code, Cursor, Codex, or GitHub Copilot.

Applied AI requirements

• Production LLM experience with prompt design, structured outputs, function and tool calling, and multi-step agent workflows.
• Experience with RAG, embedding models, vector search, and tool-use standards such as MCP; know when simple retrieval is preferable.
• Direct experience with at least one provider API: Anthropic, OpenAI, Azure OpenAI, or Snowflake Cortex.
• Design evaluations, monitoring, and guardrails, and define success before launch.
• Assess build versus buy, vendor AI features, and when AI is not the right solution.
• Have deployed an AI workflow in a live business process and be able to explain what broke and what changed.

Business and security judgment

• Map work with business users and identify steps that can be removed; communicate with executives, frontline users, and technical peers.
• Apply least privilege, secrets management, dedicated service identities, and care with applicant, resident, and employee data.
• Give honest assessments of what AI can and cannot reliably do.

Preferred experience

• Snowflake, including Cortex, and agents built over semantic layers or governed data models.
• Azure Data Factory, Power Automate, Agent 365, or enough dbt familiarity to read data models.
• Containers and scheduled or long-running cloud workloads.
• Property management, real estate, housing, or another business with distributed field operations.

Working principles and governance

• Use governed, well-defined data and identify when required data is not yet available.
• Use AI in daily work while keeping people accountable for consequential decisions.
• Ship in small pull-request-sized steps and prove reliability before expanding access.
• Every solution must have an owner responsible for monitoring, exceptions, user support, and updates.
• Follow the AI usage policy and intake process; involve Legal and HR early when use cases touch applicant, resident, or employee data.
• Give agents and integrations dedicated identities, least-privilege access, and traceable logs; do not use shared API keys or production credentials in code.