AI-LLM Systems Engineer

About the role

We are looking for a senior engineer to help build and scale Jack, JackWestin’s AI-powered learning assistant. Jack is intended to become an intelligent interface across the learning platform, helping students understand questions, access relevant learning resources, receive personalized guidance, and eventually interact conversationally with broader platform functionality.

This person should combine strong product engineering fundamentals with hands-on experience building production LLM applications. You will work closely with Product to translate user and business problems into robust AI-enabled experiences and will be expected to contribute to technical discovery and architecture, not simply execute predefined tickets.

Responsibilities

• Design, build, and maintain end-to-end AI-powered product experiences.
• Develop backend services, APIs, and platform integrations supporting Jack.
• Integrate LLMs, retrieval systems, embeddings, vector databases, tool calling, and agentic workflows where appropriate.
• Evaluate architectural approaches for RAG, contextual grounding, personalization, model routing, caching, and tool use.
• Build reliable mechanisms for passing learner, question, content, and platform context to AI systems.
• Collaborate with Product to assess feasibility, technical risk, cost, latency, and expected product value before development.
• Implement observability and monitoring for AI workflows, including failures, latency, token usage, and cost.
• Support experimentation across models, prompts, retrieval strategies, and orchestration approaches.
• Contribute to AI evaluation and regression-testing infrastructure.
• Design systems that are scalable, secure, maintainable, and privacy-conscious.
• Work closely with frontend, platform, data, QA, and instructional teams.

What we’re looking for

• Strong professional experience in full-stack or backend software engineering.
• Strong experience designing and working with APIs and distributed services.
• Production experience building applications using LLM APIs.
• Understanding of prompting, RAG, embeddings, semantic search, retrieval, tool calling, and agent workflows.
• Familiarity with model evaluation, observability, latency optimization, and inference-cost trade-offs.
• Ability to reason about AI system failure modes and non-deterministic behavior.
• Strong product mindset and ability to work effectively with incomplete requirements and ambiguity.
• Ability to challenge assumptions, propose alternatives, and participate in product and technical discovery.

Nice to have

• Experience with EdTech or adaptive learning products.
• Experience with personalization or recommendation systems.
• Experience with multimodal AI.
• Experience building AI evaluation pipelines.
• Familiarity with learner data, content-management systems, or educational platforms.

What We Offer

• 100% remote, full-time position
• $2,000–$3,000/month (depending on experience)
• Real ownership and impact