Applied AI Engineer

We’re looking for a hands-on Applied AI Engineer to build the AI tools, agents, and automations that make Ignitium faster, and increasingly, to build custom AI solutions and PoCs for our clients. AI-assisted development: We expect you to use AI coding tools aggressively. They’re core to how we work. AI assistance multiplies engineering skill, it doesn’t replace it. You must be able to read, debug, and own what you ship. Key Responsibilities Internal AI Tools & Automations (core of the role) Design, build, and maintain AI-powered tools, agents, and workflows used daily by internal teams. Translate ambiguous business problems into solutions with clear inputs, outputs, and success metrics. Harden what you build: error handling, logging, monitoring, and graceful failure for unattended workflows. Client-Facing PoCs & Custom Builds Build custom AI solutions, demos, and PoCs for client needs, adapting internal patterns to client data and systems. Prototype rapidly, evaluate against real data, and iterate. Document PoCs and support hand-off into productionized implementations. AI Platform & Best Practices Work fluently with LLM APIs (Anthropic, OpenAI) and agentic tooling (Agent SDKs, MCP, skills). Apply best practices for context design, model selection, evaluation, guardrails, and data handling. Contribute reusable components and patterns so every build makes the next one faster. Partner with non-technical stakeholders to surface pain points worth automating. Explain trade-offs (cost, latency, accuracy, reliability) in plain language. Required Qualifications Engineering Fundamentals (non-negotiable) Deep comfort with APIs, webhooks, auth, JSON, and integrating SaaS systems that were never designed to talk to each other. Solid practices: Git, testing and debugging discipline, and an instinct for when a quick script is fine versus when something needs to be built properly. Proven ability to take a vague request and ship a working solution end-to-end. Applied AI Experience Hands-on experience building production (or production-like) applications with AI integration. Working knowledge of prompt and context engineering, RAG, structured outputs, tool use, and agent architectures. Experience with a workflow automation platform (n8n preferred; Zapier or Make also valued), including writing custom code inside it. Understanding of model trade-offs: latency, cost, accuracy, and when a cheaper model is the right call. Soft Skills Bias toward action. You’d rather ship a v1 this week than design a perfect system next month. Comfortable breaking fuzzy problems into small, testable steps. Clear written and verbal communication with non-technical stakeholders. Nice to Have Building or consuming MCP servers, or working with the Claude Agent SDK or agentic frameworks. Vector databases, search systems, or LLM evaluation frameworks. Background in B2B SaaS, GTM operations, RevOps, ABM/ABX, or agency environments. What Success Looks Like (First 12 Months) Multiple internal AI tools shipped, actively used, and trusted, with stakeholders able to point to hours saved or quality gains. Client-facing PoCs and custom builds that helped win, retain, or expand client relationships. Automations that keep working: they fail loudly, recover gracefully, and don’t need babysitting. A growing library of reusable components and patterns that others can build on without you in the room. #J-18808-Ljbffr