• Build and evolve MAIA's core product capabilities • Focus on backend and AI systems, including RAG pipelines and LLM integrations • Collaborate closely with Product, DevOps, and customer-facing teams • Design, implement, and ship features from discovery through production rollout

• You build and evolve MAIA's core product capabilities. • Your primary focus is backend and AI systems - RAG pipelines, retrieval strategies, agentic workflows, and LLM integrations. • You also implement the frontend changes needed to ship features end-to-end, while backend remains your main area of work. • You design, implement, and ship features from discovery to production rollout, with a strong focus on backend and AI functionality. • You build and iterate on RAG pipelines, retrieval strategies, and LLM integrations, making pragmatic tradeoffs across quality, latency, and cost. • You build evaluation approaches for LLM features - quality gates, regression detection, and observability that makes non-deterministic systems debuggable. • You implement frontend changes needed to ship features end-to-end - simple, intuitive UI work that unblocks delivery, typically a small portion of total effort. • You proactively scout new technologies and approaches, translate findings into production-ready solutions, and push the team's understanding of what is possible. • You collaborate closely with Product, DevOps, and customer-facing teams to turn requirements into high-quality, maintainable software.

• Develop end-to-end Generative AI solutions, from technical design to production deployment and operation. • Lead or support the creation of copilots, automations, and assistants for clients and internal teams, ensuring quality, security, and scalability. • Evolve the LLMOps platform with a focus on governance, traceability, observability, cost, and security. • Work collaboratively with architecture, engineering, product, and operations teams to define and implement solutions with direct business impact. • Define and disseminate CI/CD best practices applied to Generative AI, in on-premises and cloud environments. • Investigate production failures and incidents, conduct root cause analysis, and propose structural improvements. • Promote technical best practices, perform code reviews, standardize solutions, and share knowledge across teams.

• Implement AI-powered product features and workflows based on specifications from senior engineers. • Write, iterate on, and manage production prompt templates, following established patterns for dynamic prompting and context injection. • Integrate structured output schemas (JSON mode, function calling, Zod/JSON schemas) to ensure AI responses are predictable and application-ready. • Build and maintain output enforcement mechanisms such as validators and repair loops under senior guidance. • Participate in prompt experimentation workflows — drafting variants, running A/B tests across models via OpenRouter, and documenting results. • Contribute to evaluation pipelines and help score prompt/model quality using Langfuse. • Write clean, maintainable TypeScript code within the Next.js / Node.js stack. • Participate in code reviews and incorporate feedback. • Document technical decisions and system behaviour to support knowledge sharing. • Collaborate with product, growth, data, and billing teams to deliver features on time.