About The Position

At Pencil, we are driving innovation in advertising technology through our state-of-the-art SaaS product, which harnesses Generative AI to redefine content creation. Our mission is to make AI the default in advertising without replacing creative people. To achieve this, we need to make sure that our technology isn’t just in the hands of big brands - we need to try to help small businesses and creative individuals too. We’re looking for a Head of Agent Architecture: someone who thinks in systems, not just sentences, and who can translate that thinking into a team, a roadmap, and a set of standards the rest of the company builds on. You’ll set the technical vision for agent logic, tool-calling structures, and evaluation loops across Pencil’s core creative engine and our bespoke client work — and you’ll lead a small team of Agent Architects who help you build it. This is a player-coach role. You’ll spend real time in the architecture yourself, especially on the hardest problems, while also building the team, processes, and standards that let Agent Architecture scale beyond you. You'll also represent Pencil's agent technology directly with brand and agency stakeholders, lead discovery on the most strategic engagements, and set the standard for how your team decomposes client problems and explains complex technical decisions in plain language.

Requirements

  • 8+ Years of Direct GenAI Experience, with 2+ Years Leading People or a Function: Deep, technical fluency with LLMs (GPT-4, Claude, Gemini) and multimodal models (Stable Diffusion, Midjourney, video gen), plus a track record of managing engineers/architects or owning a function’s roadmap and outcomes.
  • Systems Thinking: You think about the latent space, the context window, and how one agent’s output becomes another’s input — and you can teach that thinking to a team.
  • Technical Literacy: Comfortable with Python, JSON structures, and API documentation. Experience with agent orchestration patterns (task decomposition, tool use, state management) matters more than any specific framework. You should still be able to get into the weeds when a problem demands it.
  • Evaluation Obsession: You believe unmeasured prompts shouldn’t ship, and you’ve built or run benchmarking/A-B testing practices — not just used them.
  • Leadership & Influence: You’ve hired and grown technical people before, or you’ve owned a roadmap with real stakeholder pressure. You can set a strategic vision, get it approved by senior leadership, and hold a team accountable to it.
  • Client-Facing Problem Decomposition: Demonstrated experience leading discovery with senior customers or stakeholders and turning vague briefs into scoped technical solutions. Solutions architecture leadership, forward-deployed engineering, or technical consulting backgrounds fit well here.
  • Plain-Language Communication: You can explain agent failure modes, eval results, and architectural trade-offs to a CMO without jargon — and you hold your team to the same standard.
  • The "Creative/Technical" Bridge: You can sit in a room with a Creative Director and translate "make it feel more punchy" into a concrete change to the system — and you can teach your team to do the same. You are comfortable being the face of the technology in client meetings, not just the person behind it.

Nice To Haves

  • You find “hallucinations” a logic puzzle to solve, not just a bug — and you like teaching others to solve them too.
  • You'd rather sit with a confused client and untangle their problem than receive a perfect spec — and you hire people who feel the same.
  • You’re excited by the challenge of making an AI follow a 50-page brand book with 100% fidelity, and by building the team and standards that make that repeatable.
  • You want to build the infrastructure — and the people — that define how the next generation of advertising is created.

Responsibilities

  • Define Pencil’s technical vision and roadmap for agent architecture — multi-agent workflows, task decomposition, state management, and tool-use (RAG, API integration, etc.) — and get buy-in from leadership.
  • Hire, mentor, and manage a small team of Agent Architects. Set the technical bar, give real-time feedback, and run their development conversations.
  • Use and champion evaluation frameworks so agent performance is measured.
  • Own the reusable agents and prompt libraries that let the platform serve 1,000+ brands with unique voices simultaneously, and make the call on what gets built once versus build bespoke.
  • Partner with AI Engineering, Product, and Sales/Client leadership to decide what’s handled via prompting, RAG, or fine-tuning.
  • Act as the final technical escalation point for the most complex client deployments. Personally lead discovery on the highest-stakes engagements, decompose ambiguous client problems into buildable agent workflows, and present trade-offs (cost, latency, reliability) to senior non-technical stakeholders. Coach your team to do the same.

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 UK employees
  • Flexible working hours
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service