Senior AI Software Engineer - Aveni

Aveni is redefining how financial institutions use AI. We build real, production-ready agentic systems that reshape how banks, advisers, and financial services firms operate, replacing fragmented processes with intelligent, end-to-end workflows. Backed by leading investors including Puma Private Equity and commercially supported by Lloyds Banking Group and Nationwide Building Society, we are scaling our team to meet growing demand.

The Role

We're seeking a hands-on Senior AI Software Engineer with strong full-stack experience to build and ship AI-powered products into production, leveraging FinLLM (the UK's first LLM for Financial Services) and other foundation models. You won’t train models from scratch—instead, you'll engineer the systems, services, interfaces, and integrations that bring those models to life for advisers, analysts, and banking teams. You'll own features end-to-end across backend, frontend, and cloud infrastructure.

Key Responsibilities

• Build production-ready, AI-powered products integrating LLM capabilities, RAG, and agentic workflows into real-world processes.
• Select models, orchestrate prompts, design systems, and implement AI tooling (e.g., LangGraph, Langfuse).
• Design evaluation, monitoring, and observability to ensure reliability and readiness for production.
• Develop scalable, event-driven microservices and APIs using Node.js and TypeScript.
• Build modern, responsive React frontends to integrate AI into customer workflows.
• Architect cloud-native systems on AWS (Lambda, ECS/Fargate, API Gateway, SQS/SNS, DynamoDB, RDS).
• Implement microservices, distributed-system principles, and strong operational controls for financial products.
• Uphold engineering best practices: clean code, automated testing, CI/CD, and operational excellence.
• Diagnose and improve production behaviours relating to reliability, latency, cost, and AI output quality.
• Mentor engineers, raise technical standards, and collaborate closely with product and engineering teams.

What We’re Looking For

Essential Experience

• Extensive software engineering background building, deploying, and running production LLM/AI applications.
• Strong hands-on experience with Node.js, TypeScript, and production React.
• Experience with prompt engineering, agentic workflows, RAG, and LLM integration.
• Knowledge of AI evaluation frameworks, monitoring, and observability.
• Deep understanding of AWS, cloud-native engineering, APIs, and integration patterns.
• Experience with microservices, messaging patterns, event-driven, and distributed architectures.
• Strong commitment to clean code, testing, and operational excellence.

Nice to Have

• Experience with NestJS or similar backend frameworks.
• Familiarity with LangGraph, Langfuse, or other AI orchestration and observability tools.
• Knowledge of AI implementation in regulated or high-trust environments (ideally financial services).
• Systematic evaluation design for LLM outputs and agentic workflows.
• Experience delivering production agentic systems.

Qualifications

• Relevant degree or equivalent practical experience (production engineering capability is prioritised over specific academic backgrounds).

Benefits

• Remote-first working across the UK with co-working spaces available
• Work abroad policy
• 34 days holiday (including flexible bank holidays) plus your birthday off
• Company-wide off-sites
• Optional Personal Development Plan
• Flexible benefits platform
• Protection essentials: Life Insurance, Income Protection, Critical Illness cover
• Pension scheme (up to 5% matched employer contribution)
• Private health and dental care
• Potential share options
• Enhanced family leave