Backend Software Engineer (LLM)

Aveni is an award-winning technology company. We use advanced AI to enable scalable efficiency for financial services companies, combining world-leading Natural Language Processing (NLP) and Large Language Model (LLM) expertise with deep financial services domain experience to drive enterprise-wide productivity. Aveni harnesses the power of voice to drive unprecedented efficiency and oversight. We’re using the latest in AI to automate and innovate, empowering businesses to achieve exceptional productivity and compliance outcomes.

Summary

We are looking for an experienced Senior Back-End Software Engineer to drive the optimisation and scalability of AI-powered applications at an enterprise level. In this role, you will design and develop robust back-end systems, productise AI models, and lead the delivery of AI agent-based platforms for high-performance and autonomous AI solutions. Collaborating with cross-functional teams, you will ensure seamless integration, maintain high development standards, and mentor junior engineers. Your expertise in Python, back-end frameworks, API integration, and AI deployment will be key to building innovative solutions for some of the UK's largest financial institutions.

Responsibilities:

• Design & Develop: Build and maintain robust, scalable back-end systems that integrate AI models into production-ready applications.     
  
• Optimise Code: Analyse and enhance existing codebases for efficiency, maintainability, and performance.     
  
• Productise AI Models: Work closely with data scientists to convert machine learning prototypes into reliable, production-grade systems.
  
• Build AI Agentic solutions: You will be responsible for designing and delivering an AI agent-based platform that delivers highly performance and autonomous AI capabilities for some of the largest of the UK's financial institutions.     
  
• Collaborate: Partner with front-end developers, DevOps engineers, and product managers to deliver seamless solutions.     
  
• Ensure Quality: Conduct code reviews, implement automated testing, and follow best practices to uphold high development standards.     
  
• Mentor: Support junior team members by providing guidance and sharing technical expertise. 
  

Requirements

Skills and Experience

We’re looking for a candidate with strong technical expertise, particularly in back-end development and AI applications. You should have: 

• Minimum qualifications: Relevant commercial experience with a BSc in Computer Science or related field.      
  
• Programming Proficiency: Advanced skills in Python, with a focus on writing clean, efficient, and maintainable code. Knowledge of other programming languages (Java, Typescript, C++) will be considered an asset.     
  
• Frameworks & Tools: Experience with back-end frameworks such as Django, Flask, FastAPI or Spring Boot.
  
• APIs & Integration: Strong understanding of RESTful APIs and experience in building microservices architectures.
  
• Data Systems/Pipelines: Proficiency in working with SQL and NoSQL databases (e.g., PostgreSQL, MongoDB) and data processing ETL pipelines.       
  
• AI Integration: Experience in integrating machine learning models into production environments, ensuring they are robust and performant.
  
• Code Optimisation: Expertise in profiling and optimising back-end systems to achieve low-latency, high-throughput applications.     
  
• Version Control: Mastery of Git and experience with CI/CD pipelines to streamline development workflows.
  
• Problem-Solving: A strong analytical mindset and the ability to tackle complex technical challenges effectively.
  

• Cloud Expertise: Hands-on experience with AWS, Azure, or Google Cloud, including deployment and scaling of cloud-based applications.
  
• Programming Proficiency: Strong knowledge of Typescript and Java.
  
• Information Retrieval: Knowledge of building retrieval augmented generation (RAG) systems, with vector databases and information retrieval, such as using Elasticsearch or other search indexing solutions.
  
• Knowledge of Language Models: Understanding how large language models like GPT-3 or custom transformer-based models can be used, fine-tuned, and deployed for NLP tasks in production.
  
• Model Deployment: Experience deploying machine learning models, particularly NLP models, in production at scale using frameworks like TensorFlow Serving, TorchServe, ONNX, cloud-based ML services (e.g., AWS SageMaker, GCP AI Platform) or orchestration frameworks like Kubernettes.
  
  

Benefits