Summary
✨ AI‑Generated
A hands-on engineering opportunity for a Python specialist experienced with LangGraph and modern LLM technologies. You will design, test, and deploy reliable AI agents capable of executing multi-step workflows, calling tools, interacting with APIs and databases, retrieving information, and operating in production. The role emphasizes strong software engineering practices and taking AI solutions beyond prototypes.
Highlights
Hands-on role building production-grade AI agents and multi-step workflows. Opportunity to work on modern LLM technologies, complex software problems, enterprise integrations, and reusable engineering frameworks.
Description
We are looking for a Python Engineer with hands-on LangGraph experience to build and deploy production-grade AI agents and agentic workflows.
You will combine strong Python software engineering with modern LLM technologies to develop AI systems that can execute multi-step tasks, interact with business systems, use external tools, retrieve information, and operate reliably in production environments.
This is a hands-on engineering role for someone who enjoys solving complex software problems and has experience taking AI/LLM solutions beyond prototypes into production.
Requirements
Python & AI Agent Development
Design, develop, test, and maintain AI agent applications using Python and LangGraphBuild stateful, multi-step agent workflows with branching, looping, retries, and error handlingImplement tool calling and integrations that allow agents to interact with APIs, databases, and enterprise systemsDevelop reusable components and frameworks for agentic applicationsIntegrate LLMs into robust software applications rather than treating them as standalone chat interfaces
LangGraph Engineering
Build and maintain LangGraph-based workflows and agentsImplement state management, persistence, checkpoints, and workflow recoveryDevelop human-in-the-loop workflows and approval mechanismsDesign appropriate single-agent and multi-agent architecturesOptimise agent workflows for reliability, latency, scalability, and cost
Production Engineering
Deploy AI applications into production environmentsBuild APIs and services around AI agentsImplement testing, logging, monitoring, tracing, and error handlingTroubleshoot production issues and improve application reliabilityContribute to CI/CD pipelines and automated deployment processes
LLM and RAG Integration
Integrate commercial and open-source LLMs into production applicationsImplement prompt templates, structured outputs, function/tool calling, and context managementDevelop RAG solutions using enterprise data sourcesWork with embeddings and vector databases where appropriateEvaluate model performance and optimise model selection, latency, and cost
Enterprise Integration
Integrate AI agents with REST APIs, databases, SaaS platforms, and internal business systemsDevelop secure tools and interfaces for agents to perform business actionsImplement appropriate authentication, authorisation, validation, and access controlsEnsure agent actions are auditable and appropriately controlled
Required Experience
Strong commercial experience with PythonHands-on experience developing applications using LangGraphExperience building and deploying LLM-powered applications or AI agentsExperience developing production APIs and backend servicesStrong understanding of software engineering principles, testing, version control, and CI/CDExperience with REST APIs and enterprise system integrationUnderstanding of LLM concepts including prompting, tool calling, structured output, embeddings, and RAGExperience deploying applications on AWS, Azure, or GCP
Desirable Skills
LangChain / LangSmithMulti-agent architecturesVector databasesKubernetes and DockerInfrastructure as CodeEvent-driven architecturesAI observability and evaluationAI security and guardrailsPostgreSQL or other relational databasesRedis or similar caching technologies
