Senior AI Application Engineer
About The Position
The Senior AI Application Engineer is a senior technical builder and architect responsible for designing, building, and deploying production-grade AI-powered tools, automations, and intelligent systems across Channel Partners. This role goes beyond execution — the Senior engineer shapes the technical direction of our AI application portfolio, makes architectural decisions, drives quality standards, and serves as the internal expert on AI tooling and LLM frameworks. We’re looking for someone with 4–8+ years of software engineering experience, including at least 2–3 years in production AI/LLM application development. You have shipped real AI systems — not just prototypes — and you have the architectural judgment to know when to use what and why. You can work with minimal direction, lead technical scoping conversations, and mentor others without being asked. This role follows a hybrid, remote-flexible work model with opportunities for onsite collaboration as needed. Minimal travel is expected.
Requirements
- Bachelor’s degree in Computer Science, Engineering, or related technical field — or equivalent demonstrated expertise through shipped work.
- Portfolio of production AI applications required; GitHub, deployed tools, or detailed project case studies strongly preferred.
- Experience in agency, startup, or high-velocity delivery environments is a strong plus.
- Experience integrating AI tools with marketing automation, CRM, or enterprise platforms a plus.
- 4–8+ years of software engineering experience, with 2–3+ years focused on production AI/LLM application development.
- Deep hands-on experience with LLM frameworks — LangChain, LangGraph, LlamaIndex, OpenAI/Anthropic SDKs, Hugging Face; able to reason about trade-offs across them.
- Demonstrated experience building and deploying RAG systems — including vector database selection, chunking strategies, hybrid search, and evaluation pipelines.
- Experience with agentic AI architectures — multi-agent systems, tool use, memory, and orchestration patterns.
- Strong Python engineering — clean, testable, production-quality code; JS/Node.js a plus.
- Experience deploying LLMs or AI tools in private/closed environments (on-prem, private cloud, VPC); security-conscious design.
- Proficiency with automation platforms (n8n, Make, Zapier) and API integration patterns.
- Experience with CI/CD pipelines and cloud environments (AWS, GCP, or Azure).
- Architectural judgment — knows when to use RAG vs. fine-tuning, LangChain vs. custom orchestration, agent vs. workflow; makes defensible technical decisions.
- Senior builder instinct — moves from ambiguous problem to working architecture quickly, without needing the spec handed to them.
- Production mindset — builds for reliability, observability, and maintainability, not just for the demo.
- Technical communicator — explains trade-offs clearly to non-technical stakeholders and writes documentation that actually gets used.
- Multiplier — elevates the engineers around them through code review, mentorship, and shared standards.
Nice To Haves
- Experience in agency, startup, or high-velocity delivery environments is a strong plus.
- Experience integrating AI tools with marketing automation, CRM, or enterprise platforms a plus.
- JS/Node.js a plus.
Responsibilities
- Own the full lifecycle of AI application development — from technical scoping and architecture through build, testing, deployment, and ongoing maintenance.
- Design and implement production-grade AI-powered tools including LLM-integrated workflows, intelligent automations, internal assistants, chatbots, and RAG-based retrieval systems.
- Define and enforce AI architecture standards — selecting frameworks, establishing integration patterns, and documenting decisions the broader engineering team can build on.
- Lead technical discovery with internal stakeholders — translating ambiguous business problems into clear, scoped engineering specifications.
- Support LLM training, fine-tuning, and private/on-prem deployment in secure, closed environments where required.
- Evaluate and recommend AI tooling, frameworks, and infrastructure; stay current with the rapidly evolving LLM and agentic AI landscape.
- Build and maintain evaluation frameworks to measure AI tool performance, accuracy, latency, and cost at scale.
- Mentor junior engineers and serve as a technical resource for the broader team on AI architecture, prompt engineering, and best practices.
- Produce thorough technical documentation: architecture decisions, integration patterns, deployment guides, and operational runbooks.
Benefits
- Health and wellness benefits plans
- Flexible vacation and holiday policies
- Paid parental leave
- 401(k) with employer matching
- Technology allowance
- Referral bonus
- Tax savings with flexible spending accounts for parking, transit, dependents, and healthcare costs
- Opportunity to work with a growing company that actively rewards and promotes its employees
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
Associate degree
