Agentic Builder

Emplifi is a leading AI-powered social media marketing and customer experience platform, empowering brands to deliver meaningful, connected experiences across digital channels. Recognized as a Leader by renowned analysts and celebrated as a customer favorite, Emplifi provides innovative, data-driven insights and AI-powered tools to help brands optimize social media performance, elevate their influencer marketing strategies, and deliver impactful customer engagement across marketing, commerce, and care.

We're not running an AI pilot. We're not building a chatbot. We're systematically rebuilding every repeatable workflow in the company — across Sales, Marketing, Finance, CS, HR, Legal, and Operations — on an AI-native foundation. We call this program AI Pioneer, and it is the defining internal initiative of the next 18 months at Emplifi. The Agentic Builder role is the engine of AI Pioneer.

You'll be embedded directly into business teams, operating inside a federated model: a small central hub provides governance and shared tooling (LLM gateway, eval harness, MCP server registry); you ship inside the business. This is a hybrid role: part workflow engineer, part systems thinker, part domain translator. Industry calls it Forward Deployed Engineer or AI Solutions Engineer. This is not a consulting role. You don't recommend and move on; you build, you ship, and you own whether it works.

• Embed within business teams to map existing workflows, identify automation opportunities, and prioritise by impact and feasibility.
• Translate business goals into concrete agentic workflow specifications — defining inputs, outputs, decision logic, and human-in-the-loop touchpoints.

• Design and ship end-to-end AI workflows using no-code/low-code platforms (Make, or equivalent) and LLM-powered tools.
• Engineer prompts as production assets — versioned, evaluated, regression-tested. Not vibes. Reusable prompt chains over one-shot cleverness.
• Integrate with APIs, CRMs, data warehouses, and internal tools — comfortable with JSON payloads, webhooks, and auth patterns without needing to write full backend code.
• Use AI coding assistants (Claude, Gemini, ChatGPT, and Cursor)to produce, adapt, and debug scripts.

• Act as the in-team AI expert for your assigned function — training colleagues, documenting workflows, and building institutional knowledge.
• Collaborate with central engineering and the AI Pioneer Governance team when workflows require production infrastructure, security review, or data pipeline work.

• Maintain and improve shipped workflows based on usage feedback; establish monitoring, fallback logic, and human escalation paths.
• Surface reusable patterns and components across functions, and contribute to the organisation's agentic playbook.

• Advanced prompt engineering — systematic, versioned, regression-tested. You've shipped prompt chains that survive contact with real users, not just demo data.
• Proficient with no-code/low-code automation tools at the complex end of the spectrum: multi-step workflows, conditionals, error handling, loops.
• API literacy without hand-holding: read docs, handle OAuth/API keys, parse JSON, paginate, retry, respect rate limits.
• Understands data shapes and how poorly formatted output breaks downstream steps.
• Can read, lightly edit, and debug code (Python, JavaScript) produced by AI coding assistants.
• Familiar with LLM concepts: context windows, temperature, tool use, structured outputs, RAG basics.
• Eval and observability mindset: You instinctively reach for an eval harness before a workflow goes live. You know that "it worked when I tested it" is not a release criterion.
• Cost awareness: you can estimate token cost per run, spot a workflow that will bankrupt itself at scale, and choose model tier (Haiku/Sonnet/Opus or equivalent) deliberately.

• Thinks in workflows, not tasks — naturally maps processes end-to-end before touching a tool.
• Comfortable designing for failure: edge cases, fallback paths, and human escalation.
• Can scope what should and shouldn't be automated — knows when a human decision is irreplaceable.

• Can sit in a business team conversation and extract the automatable signal from the noise.
• Understands enough about functional operations (finance cycles, campaign pipelines, hiring workflows, CS escalations) to build for how teams actually work, not how they say they work.
• Can explain why something works (or doesn't) to people who don't code — without talking down to them or hiding behind jargon.

• Recognize when a workflow touches personal data, financial data, customer data, or regulated content and route to central governance before shipping, not after.
• Understand basic threat surface: prompt injection, data exfiltration via tool calls, over-permissioned agents, secret handling.
• Comfortable with audit trails, access scoping, and "least privilege" defaults.

• Ships working solutions — demonstrates bias toward done over perfect, with a clear standard for what 'done' means.
• Owns outcomes, not just outputs — follows through on whether the automation is actually being used and delivering value.

• Earns trust quickly within business teams by demonstrating domain curiosity and delivering fast.
• Comfortable operating as a change agent in teams that may be skeptical — wins people over through results, not persuasion.
• Knows when to escalate and involve central engineering — and how to hand off cleanly.