Software Engineer

This is a hands-on role for engineers with strong full-stack development experience and practical expertise in large language models. You will take AI solutions from concept or prototype through to production, including deployment within cloud and self-hosted environments. You will be expected to work independently, make sound technical decisions, and take end-to-end ownership of delivery. Responsibilities

• Design, build, and maintain production-grade AI applications and services
• Convert AI prototypes into secure, reliable, and scalable production systems
• Develop full-stack solutions across front end, back-end, APIs, databases, and infrastructure
• Deploy and operate applications on AWS, Google Cloud, and self-hosted infrastructure
• Build LLM-powered workflows, agents, retrieval-augmented generation systems, integrations, and automation
• Integrate AI applications with internal systems, databases, APIs, and third-party platforms
• Evaluate models, architectures, and tools based on accuracy, reliability, latency, security, and cost
• Implement appropriate testing, evaluation, monitoring, logging, and observability
• Diagnose technical and production issues, identify root causes, and own resolution
• Make pragmatic engineering decisions that balance delivery speed, quality, maintainability, and operational risk
• Own solutions throughout their life cycle, from architecture and development to deployment and continuous improvement Required Experience Software Engineering
• Strong commercial experience with JavaScript, Type Script, and Python
• Experience building back-end services and REST APIs
• Strong knowledge of SQL, relational databases, and data modelling
• Experience developing and maintaining full-stack applications
• Proficiency with Git, automated testing, code review, and modern development practices Cloud and Infrastructure
• Production experience with AWS and/or Google Cloud Platform
• Experience with Docker and containerised application deployment
• Practical knowledge of CI/CD pipelines
• Experience deploying and operating self-hosted applications
• Strong understanding of production monitoring, logging, security, and troubleshooting AI and LLM Engineering
• Proven experience building and deploying LLM-powered applications in production
• Experience working with commercial and open-source language models
• Strong understanding of prompt design, context management, structured outputs, and tool calling
• Experience with RAG, embedding, vector databases, and retrieval systems
• Experience building agentic or multi-step AI workflows
• Understanding of LLM evaluation, observability, reliability, latency, and cost optimisation
• Effective use of AI-assisted development tools to improve engineering productivity Experience with technologies such as MCP, LangGraph, LangChain, LlamaIndex, Kubernetes, Terraform, or equivalent tools is advantageous. Strong engineering judgement and the ability to select the right technology are more important than experience with any specific framework. What We Are Looking For
• Ability to turn ambiguous business requirements into clear, practical technical solutions
• Strong ownership and accountability from problem identification through to production delivery
• Ability to work effectively with minimal supervision
• A solution-oriented approach to technical and operational challenges
• Strong root-cause analysis and problem-solving skills
• Clear communication of technical options, trade-offs, risks, and recommendations
• Ability to work across the technology stack when required
• Capacity to learn unfamiliar technologies and codebases quickly
• Focus on measurable outcomes rather than task completion alone
• Ability to move quickly while maintaining appropriate engineering standards What Success Looks Like You can take ownership of a business problem without requiring a detailed implementation plan, determine the most appropriate technical approach, communicate your recommendation clearly, and deliver a reliable production solution. You are comfortable building quickly, working across the stack, resolving complex technical issues, and taking responsibility for the ongoing performance of the systems you deliver. To apply for this role please submit your CV to hiring@besque.com.