CT - Full Stack AI Engineer
Anonymized Job Summary
We are building a next‑generation operating environment for modern enterprise workflows, with AI at its core. As a Full Stack AI Engineer, you will own the end‑to‑end design and delivery of AI‑powered features that make the platform intelligent. This includes developing agentic workflows, APIs, and user interfaces through which users interact with AI copilots, predictive tools, and automated pipelines - from concept to production.
This is a high‑ownership role for someone who thinks in full systems. You won't hand things off at the API boundary - you'll own the experience from the data layer to the UI. You will work directly with senior AI/ML leadership and sit at the intersection of product, engineering, and applied AI. Your initial focus will be on several high‑priority AI initiatives tied directly to revenue growth and product differentiation.
You will collaborate closely with the ML Engineer, who owns the intelligence layer (models, features, evaluation). You own the application and orchestration layer that delivers that intelligence to end users.
Responsibilities
Agentic AI & LLM Systems (Primary Ownership)
- Design, build, and maintain modular AI agents that automate multi‑step workflows across internal modules.
- Own RAG pipelines, retrieval architectures, and semantic search systems grounded in structured business data.
- Implement guardrails, evaluation frameworks, and human‑in‑the‑loop review processes for agentic systems.
- Integrate LLMs (commercial or open‑source) into user‑facing features.
Full Stack Development
- Design and build scalable, production‑grade applications across both frontend and backend.
- Create intuitive AI‑native user experiences: chat interfaces, copilot‑style tools, workflow automation surfaces.
- Own features end‑to‑end - data modeling, API design, UI development, and deployment.
Platform & Infrastructure
- Deploy and maintain services using containerization and cloud platforms.
- Ensure AI‑powered features are reliable, observable, and performant in production.
- Collaborate with ML engineering to integrate model outputs and feature pipelines into user‑facing surfaces.
- Maintain high code quality via testing, code reviews, and CI/CD ownership.
- Work with data engineering teams to integrate internal pipelines, third‑party API feeds, event‑driven flows, and ETL outputs.
Iteration & Product Thinking
- Rapidly prototype and validate new AI‑powered capabilities based on user feedback.
- Contribute to architectural decisions with a bias toward shipping quickly and learning.
- Communicate technical tradeoffs clearly with engineering, product, and business teams.
- Perform other duties as assigned.
Qualifications
Required
- 5+ years of software engineering experience with a history of shipping production applications.
- Hands‑on experience building agentic or multi‑step AI workflows in production.
- Strong proficiency in a modern frontend framework (e.g., React, Next.js) and backend language (Python or Node.js).
- Experience integrating LLMs or AI APIs into real user‑facing products.
- Familiarity with RAG systems, vector databases, and embedding‑based retrieval.
- Experience designing and documenting RESTful APIs.
- Proficiency with relational databases (PostgreSQL or similar).
- Solid understanding of Kubernetes, Docker, and DevOps practices (CI/CD, observability, deployment workflows).
- Experience in AI evaluation - output quality assessment, hallucination detection, and eval framework design.
- Comfortable using AI‑native developer tools.
- Ability to work independently and own features end‑to‑end.
Preferred
- Experience at a startup or early‑stage engineering environment.
- Portfolio of AI‑related projects (RAG systems, LLM agents, copilot tools).
- Familiarity with industry‑specific operations or data workflows.
- Knowledge of data privacy, compliance, and responsible AI deployment considerations.
- Experience with AI‑native development tools.
Tech Stack
Frontend: React, Next.js, TypeScript, Tailwind CSS
Backend: Python (FastAPI), Node.js
AI & Agent Frameworks: LangChain, LangGraph, DeepEval, MCP
Vector & Retrieval: Pinecone, Weaviate, or equivalents
Databases & APIs: PostgreSQL, Snowflake, RESTful API design
Infrastructure: Docker, Kubernetes, major cloud providers
Collaboration & Dev Tools: GitHub, Linear, modern AI‑assisted coding tools
FAQs
Congratulations, we understand that taking the time to apply is a big step. When you apply, your details go directly to the consultant who is sourcing talent. Due to demand, we may not get back to all applicants that have applied. However, we always keep your CV and details on file so when we see similar roles or see skillsets that drive growth in organisations, we will always reach out to discuss opportunities.
Yes. Even if this role isn’t a perfect match, applying allows us to understand your expertise and ambitions, ensuring you're on our radar for the right opportunity when it arises.
We also work in several ways, firstly we advertise our roles available on our site, however, often due to confidentiality we may not post all. We also work with clients who are more focused on skills and understanding what is required to future-proof their business.
That's why we recommend registering your CV so you can be considered for roles that have yet to be created.
Yes, we help with CV and interview preparation. From customised support on how to optimise your CV to interview preparation and compensation negotiations, we advocate for you throughout your next career move.