AI Engineer
Posted on:
July 3, 2025
Job description
The Stealth
We’re spinning up a brand new product (think fast moving, lower touch sales/PLG, not your typical enterprise SaaS beast), and we’re on the hunt for an AI Engineer with serious founder energy to help bring it to life.
You’ll be designing, prototyping, and deploying AI-powered product from day one, working closely with two of our co-founders, Tom and Tim (we like to keep the names simple, but the ideas bold). This is your chance to make your mark, all while backed by the resources of a scaling startup that’s already nailed product market fit in multiple countries.
If you're craving impact, autonomy, and a bit of chaos (the fun kind), look no further.
Responsibilities
Key aspects of this role
This role is equal parts builder, experimenter, and problem solver. You’ll play a central role in designing, developing, and shipping AI-powered capabilities that deliver real value to our customers.
- Design and develop LLM applications, using Langchain, LangGraph, and related frameworks, with a focus on building robust, production-grade workflows.
- Prototype and experiment rapidly—you’ll test different model approaches, pipelines, and architectures to validate ideas before moving them to production.
- Own the full lifecycle of AI systems, including dataset creation, evaluation design, model orchestration, deployment, and monitoring.
- Develop backend components needed to support AI capabilities, such as inference services, data pipelines, and APIs (not general application features like user authentication).
- Work across our tech stack, primarily Typescript for production workloads, and Python for notebook prototyping in Hex.
- Collaborate cross-functionally with product and engineering teams to scope and build AI-powered experiences that are performant, reliable, and cost-effective.
- Stay up to date with advancements in LLMs and AI tooling, applying new techniques to solve customer problems and improve product capabilities.
- Contribute to technical strategy and architecture, including decisions about infrastructure, scalability, and responsible AI practices.
- Support and improve deployed AI systems in production, ensuring reliability, observability, and iterative improvement.
Tech Stack:
- Langchain/LangGraph (Typescript/Python) deployed on ECS & Lambda
- Langsmith for datasets/evals/experiments
- Hex for prototyping/notebook'ing
Job requirements
You’re ideal for the role if you have…
- Production experience deploying LLM applications, using Langchain, LangGraph, or similar frameworks.
- Experience designing evaluation frameworks for LLM applications, including dataset management, experiment tracking, and performance measurement.
- Experience supporting LLM-powered applications in production environments, including monitoring, debugging, and optimising reliability and cost.
- Proficiency in one or both of Typescript and Python. We prefer to ship production workloads in Typescript, and use Python for notebook workflows in Hex.
- Hands-on experience with backend or full-stack engineering, especially in the context of integrating AI capabilities rather than building generic application features.
- Understanding or exposure to AWS infrastructure, including how your systems are deployed and operated (ECS, Lambda, and related services).
- An entrepreneurial mindset, with high grit, focus, and a results-oriented approach. You’re comfortable iterating and figuring things out on the fly.
- Strong analytical skills, and a love for solving open-ended problems with data.
- A bias for action and ownership, you don’t wait for perfect specs, you build and validate.
- A growth mindset, always learning and sharing what you learn.
Apply now
When you apply, please mention you found the job on Aussie Intelligence. This encourages more tech companies to hire through our platform, creating more opportunities for you. Good luck with your application!
Apply now
