AI Product Engineer

Life @ Get Licensed; Karachi Division; Hybrid; PKR 2,000,000 - 3,500,000; Full time

Benefits offered by this job

Private medical insurance

Career growth

Hybrid work environment

Annual leave and holidays

Influence training delivery

Job summary

Get Licensed in the UK is seeking a hybrid Product/Engineering leader to own AI-powered product initiatives end to end. You will prototype with React/TypeScript and Python/Node, ship with the UK and Karachi teams, and measure value through experiments.

If you ship real LLM features, influence product strategy, and thrive in a fast, non-hierarchical environment, join us. We offer a competitive base salary with benefits and opportunities for career growth in a dynamic, AI-native workplace.

Qualifications

• 3+ years combined experience across product management and software engineering.
• Shipped at least one LLM-powered feature to real users.
• Hands-on coding ability in Python and/or TypeScript, shipping full-stack prototypes independently.
• Practical experience with LLM APIs (Anthropic, OpenAI, or similar), including structured outputs and tool use.
• Strong product judgement: ability to say no, prioritise ruthlessly, and justify business value.
• Clear written communication — specs, briefs, and decision docs that others can act on.

Responsibilities

• Own the product lifecycle for AI features across the GuardPass ecosystem—from discovery to ship and measurement.
• Build working prototypes using React/TypeScript front ends and Python/Node back ends.
• Design and implement LLM-powered systems including conversational interfaces, RAG pipelines, multi-agent workflows, and tool integrations.
• Develop evaluation frameworks to define what “good” means for an AI feature and drive iteration.
• Write and refine production prompts; treat prompt engineering as a versioned engineering artifact.
• Collaborate with lead engineers and PMs across UK and Karachi teams to take prototypes to production-grade services.
• Instrument funnels, latency, cost-per-conversation, containment/resolution rates and base decisions on data.
• Stay current on model landscape and make pragmatic build-vs-buy and model selection calls.

Skills

PM experience

Engineering experience

Shipped LLM feature

Backend/frontend prototyping

Product judgement

Clear written communication

Tools

Python

TypeScript

REST APIs

LLM APIs

Job description

Job Description

About Get Licensed

Get Licensed is the UKs leading platform for security training, vetting, and staffing, operating across 85+ locations. Our product portfolio — GuardPass, GuardCheck, GuardFlex, and OnSiren — serves hundreds of thousands of security professionals and the businesses that employ them. We are rebuilding core customer journeys around AI-first experiences, from conversational booking to agentic internal tooling, and we need builders who can move from idea to shipped product without waiting for a handoff.

The Role

This is a hybrid role for someone who refuses to pick between product and engineering. You will own AI-powered product initiatives end to end: identifying the opportunity, defining the experience, prototyping it yourself, and shipping it to production with the engineering team. Youll work directly with the Head of Product and founders on high-visibility bets — conversational booking flows, LLM-powered support and operations tooling, and agentic workflows that replace manual back-office processes.

You are equally comfortable writing a PRD, writing the prompt, and writing the code.

What Youll Do

• Own the product lifecycle for AI features across the GuardPass ecosystem — discovery, spec, prototype, ship, measure, iterate.
• Build working prototypes yourself (React/TypeScript front ends, Python/Node back ends, LLM APIs) rather than describing them in documents.
• Design and implement LLM-powered systems: conversational interfaces, RAG pipelines, multi-agent workflows, and tool-use/MCP integrations.
• Develop evaluation frameworks — define what “good” means for an AI feature, build evals, and use them to drive iteration rather than vibes.
• Write and refine production prompts; treat prompt engineering as a versioned, tested engineering artifact.
• Work with lead engineers and PMs across UK and Karachi teams to take prototypes to production-grade services.
• Instrument features properly: funnels, latency, cost-per-conversation, containment/resolution rates —and make decisions from the data.
• Stay current on the model landscape (Anthropic, OpenAI, open-weight models) and make pragmatic build-vs-buy and model selection calls.

What We’re Looking For

Must have

• 3+ years combined experience across product management and software engineering (in either order — but real experience in both).
• Shipped at least one LLM-powered feature or product to real users — not just demos.
• Hands‑on coding ability: comfortable in Python and/or TypeScript, working with REST APIs, and shipping full‑stack prototypes independently.
• Practical experience with LLM APIs (Anthropic, OpenAI, or similar), including structured outputs, tool use / function calling, and context management.
• Strong product judgement: you can say no, prioritise ruthlessly, and articulate why a feature matters in commercial terms.
• Clear written communication — specs, briefs, and decision docs that others can act on.

Strongly preferred

• Experience with agentic frameworks or patterns (Claude Agent SDK, LangGraph, MCP, or equivalent).
• Experience building and running LLM evals (promptfoo, custom harnesses, or similar).
• Familiarity with modern deployment stacks (Supabase, Railway, Cloudflare Workers, AWS).
• Experience in marketplaces, booking flows, or regulated industries.
• Exposure to conversational UX design — voice or chat.

Nice to have

• Prior startup or founder experience.
• Data analysis skills (SQL, basic statistics) for feature measurement.
• Design sensibility — you can make a prototype look credible without a designer.

What This Role Is Not

• A pure PM role where you brief engineers and wait. You build.
• A pure engineering role where someone else decides what to build. You own the “what” and the “why.”
• A research role. We ship to paying customers on short cycles.

How We Work

• Small, senior, fast. Prototypes over decks. Working software over roadmap theatre.
• AI-native workflows internally — we expect you to use AI tools (Claude Code, Cursor, or similar) as a force multiplier, not a novelty.
• Distributed across Karachi and the UK; async-friendly with overlap hours for UK collaboration.

Expected Behaviors

Were primarily non-hierarchical, allowing all our colleagues to take responsibility from day one. We are committed to achieving excellence whilst having fun and being highly curious. We are passionate about hiring fantastic individuals who thrive in an open, fast-paced and collaborative environment, are accountable to themselves, and are willing to roll their sleeves up to get stuff done.

There are certain behaviors we expect from our colleagues, and the key ones are below. Fundamentally we expect everyone at Get Licensed to Do The Right Thing. We measure performance against these behaviors as part of each team member’s monthly performance review:

• Agility: We move fast, adapt quickly, and continuously improve.
• Curiosity: We never stop learning and seeking better ways to do things.
• Excellence: We set new standards and strive to exceed expectations.
• Care: We care deeply for the work we do, for each other, and for our customers.
• Ownership: We take responsibility of outcomes.

What we offer

• Competitive base salary with additional benefits, including private medical insurance, and paid holiday.
• Unlimited opportunities for career growth and professional development
• The chance to influence and improve training delivery across the organization.
• Join a dedicated and professional team where your ideas are welcomed and your commitment rewarded.
• As the face of Get Licensed, you will be required to lead by example, and live the Get Licensed values to their fullest, based around Doing the Right Thing.

Requirements