Agent Architect

About the role

Pencil is building an agentic operating system for marketing, turning generative AI into a professional, brand‑safe, and scalable solution. As an Agent Architect you will design the core "brain" that powers our creative engine, turning high‑level creative intent into reliable, multi‑modal AI workflows.

Key responsibilities

• Design and implement multi‑agent workflows, including task decomposition, state management, and tool‑use (RAG, API integration, etc.).
• Develop rigorous evaluation frameworks (LLM‑as‑a‑judge, promptfoo, DSPy) to measure and improve agent performance at scale.
• Create reusable agents and prompt libraries that enable the platform to serve thousands of brands with distinct voices.
• Collaborate with AI Engineering and Product teams to decide when to use prompting, RAG, or fine‑tuning.
• Lead technical architecture for custom client deployments, translating creative briefs into deterministic AI workflows.

Required profile

• 3+ years of hands‑on experience with generative AI models (LLMs and multimodal).
• Strong systems‑thinking mindset, able to consider latent space, context windows, and inter‑agent data flow.
• Passion for measurement‑driven development; comfortable with benchmarking and A/B testing AI outputs.
• Ability to bridge creative direction and technical implementation.

Required skills

• Python programming
• JSON data structures
• API design and integration
• Experience with orchestration frameworks such as LangChain, CrewAI, or AutoGen
• Familiarity with evaluation tools like promptfoo or DSPy
• Knowledge of LLMs (GPT‑4, Claude, Gemini) and multimodal models (Stable Diffusion, Midjourney, video generation models)