Our ‘black belt’ specialists are leaders in their domains: digital champions, delivery-focused experts, top-tier security professionals, AI thought leaders, and engineering best practice advocates.
With a global presence and local expertise, we deliver innovative solutions without compromising on quality. Our multidisciplinary teams provide tailored expertise to solve complex problems at scale, ensuring engineering excellence through our top technologists.
Empower Your Career with Us
Are you ready to join a dynamic team that empowers businesses through robust engineering capabilities? We seek talented individuals who thrive in a fast-paced environment with a strong sense of urgency and a focus on execution.
Overview of the Role
We are seeking an experienced Python AI Engineer to join our cutting-edge engineering team. In this role, you will be instrumental in building, deploying, and supporting full-scale, enterprise-grade AI applications.
Building a comprehensive AI application requires a unique engineering mindset. You will not just be writing code; you will be tackling the complex reality of non-deterministic systems, managing LLM API costs at scale, and orchestrating deep AI integrations. We need an engineer who can build robust architectures using LangChain and implement the guardrails, observability, and evaluation frameworks necessary to support and optimise probabilistic AI models in live production environments.
Key Responsibilities
-
AI Application Development: Design and build full-scale, cloud-native AI applications and microservices using Python.
-
LangChain Orchestration: Utilise LangChain to construct complex agentic workflows, memory management systems, and Retrieval-Augmented Generation (RAG) pipelines.
-
Non-Deterministic Engineering & Cost Optimisation: Architect solutions that account for the probabilistic nature of Large Language Models (LLMs). This includes ensuring graceful degradation when models hallucinate or fail, while actively monitoring and optimising token usage and external API costs.
-
Production Support & Observability: Monitor, support, and debug live AI systems. This includes tracing LLM calls, tracking prompt drift, and analysing model behaviour in production.
-
Evaluation & Guardrails: Implement automated evaluation frameworks (such as LLM-as-a-judge) and output guardrails to ensure production systems remain safe, accurate, and aligned with business logic.
-
Cross-Functional Collaboration: Work closely with product owners, data scientists, and infrastructure teams to deploy AI solutions securely and efficiently at scale.
Skills & Experience
-
Programming Mastery: 5+ years of experience as a software engineer, with advanced proficiency in Python and modern API development (e.g., FastAPI).
-
AI Frameworks: Hands-on, commercial experience building full-scale applications with LangChain, including custom tool creation and agent orchestration.
-
Production AI Support: Proven experience supporting non-deterministic systems in production. You must understand how to monitor model variance, manage API costs effectively, and troubleshoot unpredictable system behaviour.
-
Cloud Architecture: Strong experience with cloud-native architectures and containerisation (Docker, Kubernetes) for deploying scalable AI workloads.
-
Engineering Best Practices: Deep commitment to CI/CD, automated testing, and writing clean, maintainable code.
Bonus Points For ✨
- Experience with AI observability platforms (e.g., LangSmith, Phoenix).
- Background in building automated testing platforms for AI applications.
- Familiarity with vector databases (e.g., Pinecone, Weaviate, or pgvector).
What We Offer
- A collaborative and innovative work environment focused on engineering excellence.
- The chance to work on cutting-edge AI projects with a team of industry leaders.
- Opportunities for continuous professional growth and development.
