AI Engineer

About Zof AI and the Role

Zof AI is looking for an experienced AI Engineer based in San Francisco, CA, to join their fast-paced team focused on building innovative AI products. This full-time position involves developing advanced features that leverage frontier large language model (LLM) APIs to enhance product capabilities. The successful candidate will be responsible for designing and owning the model-facing components, including retrieval and Retrieval-Augmented Generation (RAG) pipelines, agent orchestration, multi-agent frameworks, and context engineering to ensure AI reliability in production environments.

Key Responsibilities

• Create and enhance product functionalities built on state-of-the-art model APIs.
• Develop, optimize, and manage end-to-end retrieval and RAG pipelines.
• Architect agent planning, effective tool integration, and coordination across multiple agents.
• Implement disciplined, tested approaches to prompt and context engineering.
• Integrate evaluation mechanisms into development cycles to objectively measure quality.
• Balance and optimize cost, quality, and latency factors for AI features in live production.
• Collaborate closely with product and engineering teams to ensure timely and reliable delivery.
• Take ownership from conceptual design through to deployment of model-layer systems.

Candidate Requirements

• Proven track record of launching LLM-powered features into production environments.
• Strong foundational software engineering skills with sound architectural judgment.
• Understanding and practical experience with retrieval, RAG methodology, and agent design patterns.
• Proficiency in current model API ecosystems and related tooling.
• Proven ability to make informed trade-offs concerning feature quality, operational cost, and response latency.
• Excellent communication skills, both written and verbal, to work effectively in a fast-evolving context.
• Demonstrated history of producing high-quality technical outputs.

Preferred Qualifications

• Experience working with multi-agent frameworks or orchestrating multiple agents.
• Familiarity with evaluation harnesses for AI system assessment.
• Knowledge of programming languages and technologies such as TypeScript, Python, Node.js, and PostgreSQL.
• Experience with model fine-tuning or adaptation techniques.

Work Environment and Benefits

• Provision of high-end equipment, including MacBook Pro and premium AI development tools.
• Access to advanced AI tooling such as Cursor Ultra, Claude Code Ultra, and OpenAI Codex Max or similar.
• Opportunity to work within a high-performance AI product development setting located in the San Francisco AI ecosystem.
• Close interaction with company leadership, engineering teams, and client stakeholders.
• Support for wellness and productivity where applicable.
• Competitive startup compensation package including meaningful equity and salary.
• High level of ownership and direct influence on product outcomes.

Additional Information

This position is strictly on-site in San Francisco and aims for candidates willing to relocate if needed. The company emphasizes precision in hiring and requires completion of detailed application materials including professional background, coding proficiency levels, and personal motivations. Benefits may vary based on role specifics and final offer negotiations.