Applied AI Engineer

Responsibilities:

• Build AI applications and agents that automate post-sales workflows, onboarding health checks, usage/adoption reviews, ticket triage, knowledge-base answering, and SOAP/billing lookups.
• Design and ship internal automations across the post-sales stack (support, CRM, billing, data warehouse) so manual steps disappear.
• Develop LLM-powered features: retrieval over product docs and knowledge bases, summarization, drafting, and classification with an eye on accuracy and guardrails.
• Integrate systems via APIs and connectors (Slack, email, Jira, analytics/BI, internal Spry services) into reliable end-to-end workflows.
• Instrument everything: define success metrics, monitor quality, and iterate based on real usage.
• Partner directly with CS, onboarding, and support leads to find the highest-leverage problems and prototype fast.

Requirements:

• 2-4 years of software engineering experience, with real projects shipped to production.
• Strong Python (or TypeScript/Node) and comfort building against REST APIs and webhooks.
• Hands-on experience building with LLMs, prompt engineering, RAG, function/tool calling, and agent frameworks.
• A bias for shipping: you prototype quickly, get feedback, and iterate rather than over-engineering.
• Solid grasp of data SQL, working with structured and unstructured sources, and basic pipelines.
• Clear communicator who enjoys working alongside non-engineers and translating messy processes into clean automations.
• Experience with automation platforms (Zapier, n8n, workflow orchestration) or building internal tools.
• Familiarity with customer success/support tooling, CRMs, or BI tools (Redash, Looker, etc. ).
• Healthcare, RCM, or B2B SaaS domain experience.
• Comfort with cloud infra, evals/testing for LLM systems, and lightweight MLOps.