Founding Product Engineer

Tasks

The role

You'll own Pling's architecture and code, strategy and execution. The role is hands-on and impact-driven: you contribute to product discussions alongside the founders, then own the full technical lifecycle — architecture, implementation, deployment, monitoring, and continuous improvement in production — with a focus on real-world reliability and business impact.

Your mandate is to architect and ship the platform that takes Pling to the next 10x of customers and locations — AI-native by design, built to scale across multi-site groups across Europe — and to build the development pipeline that makes our shipping velocity hard to match.

We believe a small, AI-augmented engineering team can outship teams five times its size. You'll prove that with us.

What you'll do

• Build complete features end-to-end — data model to API to UI

• Own the technical direction — architecture, infrastructure, security, performance

• Design and own the LLM pipelines that power Pling's AI features — prompt design, structured outputs, evals, monitoring, cost tracking

• Set engineering standards across code and AI features — testing, CI/CD, observability, code review on one side; eval harnesses, regression checks, and quality metrics tied to business outcomes on the other

• Define and lead the migration to our next-generation architecture — the stack choices are yours to shape

• Build the development pipeline that makes our shipping velocity hard to match

• Hire and lead — bring on the next engineer when the time is right, and define how the team works

Requirements

Experience

• 6–9+ years building production software in fast-paced environments, with at least 2 years focused on LLM-powered features in production

• Pragmatic about architecture and tradeoffs; you've learned that good engineering usually means removing complexity, not adding it

• Comfort across the stack — backend center of gravity, but able to ship end-to-end

• Production experience with Python, TypeScript/Node.js, and modern databases (SQL and NoSQL)

AI-native fluency

• Deep practical understanding of LLM behavior: prompting, structured outputs, context window management, common failure modes, handling non-determinism, and writing evals that catch regressions before users do

• Pragmatic about model selection — pick across providers (Claude, GPT, Gemini, open-weights) based on cost, latency, and quality tradeoffs for each use case

• Know when not to reach for an LLM. A lot of good engineering is knowing when a regex, a lookup table, or deterministic code is the right answer. You hate AI slop as much as you love AI leverage.

• Follow the field actively and adopt new tools when they earn it.

Builder mindset

• You'd rather build than manage. AI excites you because it lets you ship at a scale you couldn't before.

Engineering excellence

• Code quality is a habit, not an afterthought: testing, review, quality gates

• Strong on operational excellence: security, reliability, performance, observability

• Confident with CI/CD and production deployments

Collaboration

• Clear communicator who explains technical trade-offs to founders, customers, and future hires

• Balance speed, quality, and long-term sustainability in your decisions

• Fluent English. German is a big plus — our customers operate in German