Agent Architect

At Pencil, we’re building the agentic OS for marketing. We aren't just using integrating generative AI; we are building the machine that makes it professional, brand-safe, and scalable. We’re moving beyond simple text-in/text-out interfaces toward complex multi-agent architectures that can handle the nuanced demands of global brands and the agility of small businesses.

The Role: Architecting the Creative Brain

You won’t just be "prompting"; you will engineering behavior . You will bridge the gap between creative intent and machine execution, ensuring that our agents are robust, predictable, and capable of high-fidelity output across text, image, and video.

Your work will fall into two high-impact pillars:

• Core Systems: Designing and scaling the foundational agents that power the Pencil SaaS platform.
• Client Solutions: Architecting custom workflows for world-class brands that require specific "brand DNA" and complex creative logic.

Job Responsibilities

• Agent Architecture: Design and implement multi-agent workflows, including task decomposition, state management, and tool-use (RAG, API integration, etc.).
• Systematic Optimization: Move beyond "vibe-based" testing. Implement rigorous evaluation frameworks (e.g., using LLM-as-a-judge, promptfoo, or DSPy) to measure and improve agent performance at scale.
• Scalable Frameworks: Develop reusable agents and prompt libraries that allow the platform to serve 1,000+ brands with unique voices simultaneously.
• Cross-Functional Engineering: Partner with AI Engineering and Product teams to determine which behaviors should be handled via prompting, RAG, or fine-tuning.
• Client Architecture: Act as the technical lead for complex client deployments, translating high-level creative briefs into deterministic AI workflows.

What We’re Looking For

• 3+ Years of Direct GenAI Experience: You have a deep, intuitive, and technical understanding of LLMs (GPT-4, Claude, Gemini) and multimodal models (Stable Diffusion, Midjourney, Video Gen).
• Systems Thinking: You don’t just write a prompt; you think about the latent space, the context window, and how one agent’s output becomes another’s input.
• Technical Literacy: While this isn’t a "Software Engineer" role, you should be comfortable with Python, JSON structures, and API documentation. Experience with orchestration frameworks (LangChain, CrewAI, AutoGen) is a major plus.
• Evaluation Obsession: You believe that if you can’t measure a prompt’s performance, you shouldn’t ship it. You are familiar with benchmarking and A/B testing AI outputs.
• The "Creative/Technical" Bridge: You can sit in a room with a Creative Director and translate "make it feel more punchy" into a temperature adjustment and a few-shot prompting strategy.

You’ll Thrive Here If...

• You find "hallucinations" to be a logic puzzle to be solved, not just a bug.
• You are excited by the challenge of making an AI follow a 50-page brand book with 100% fidelity.
• You want to build the infrastructure that defines how the next generation of advertising is created.

KPI & Success Measures

• System Reliability: Reducing the "failure rate" of complex agent workflows.
• Architectural Efficiency: Minimizing token usage/latency while increasing output quality.
• Brand Alignment: Scoring of agent outputs against specific brand guidelines using automated evaluation tools.
• Scale: Successful rollout of core agents used by the entire Pencil user base.

Benefits

• 25 days PTO plus public holidays, although we operate a Flexible Time Off scheme
• Health insurance / private medical cover
• Monthly stipend towards wellness, fitness, and learning and development
• Remote - work from anywhere in your home country
• Enhanced parental leave policies, whether you become a parent through birth, adoption or surrogacy
• Access to our Pencil office in The Shard, London for our UK employees
• Flexible working hours