Staff Applied AI Engineer

Role overview

A staff-level engineering role on an applied AI team, leading the technical direction of LLM-powered agents that translate natural language into production-ready, full-stack applications. The position blends deep LLM expertise with hands-on systems design, owning architecture decisions that shape how agents reason over large codebases, orchestrate multi-step workflows, and handle everything from simple UI tweaks to complex architectural changes. It is an IC role with broad cross-team influence, focused on pushing the frontier of what agentic coding tools can deliver at scale.

Responsibilities

- Define the architecture for AI agents handling context management, multi-step workflow orchestration, and scalable tool use across large codebases. - Lead a multi-model strategy, building evaluation harnesses and selection criteria across frontier providers and partnering with their teams to test emerging capabilities. - Design safe, reliable interfaces for tool calling (search, queries, domain actions) and set organizational best practices for agent frameworks. - Align product, design, and engineering on AI initiatives, resolving tradeoffs and mentoring engineers to raise the bar on AI engineering quality. - Establish data and evaluation standards, owning dataset methodology and the eval harness to convert failure modes and conversation insights into measurable improvements. - Drive research into prompting, context handling, and post-training techniques, sharing learnings externally when appropriate.

Requirements

- Proven experience building and scaling production LLM systems, with strong understanding of capabilities, limits, and emergent behavior. - Deep prompt engineering expertise, including setting best practices and mentoring across models and use cases. - Strong software engineering fundamentals, with the ability to design scalable systems and make pragmatic architectural decisions. - Track record of driving ambiguous, high-scope work end to end and influencing outcomes across teams. - Systems-level thinking: ability to spot process, communication, and technical debt and improve team velocity. - Strong verbal and written English communication skills for frequent collaboration with team members, stakeholders, and customers.

Nice to have

- Fine-tuning and alignment experience with LLMs (SFT, RLHF/RLAIF, DPO/ORPO). - Machine learning fundamentals and familiarity with model evaluation metrics. - Open-source contributions to AI or ML projects. - Experience reading and implementing techniques from research papers. - External presence through conference talks, technical writing, or industry representation.

Benefits and work setup

- Fully remote, globally distributed team. - No college degree required to apply. - Open to candidates located outside the United States. - Applicants are not expected to meet every qualification listed.