In this Full-Stack AI Engineer job, you will be working for Astra Asset Management, a hedge fund exploring the potential of advanced technology and artificial intelligence to enhance business processes and support its operations.
The business operates in a data-intensive environment where access to information, efficient workflows and reliable technology are essential. By developing AI-powered applications and intelligent systems, the team aims to streamline processes, improve knowledge retrieval and unlock new opportunities through automation.
This is an exciting opportunity to join a growing technology function, work with cutting-edge AI technologies and contribute to the development of practical AI solutions within the financial services sector.
Job description - Full-Stack AI Engineer
In this Full-Stack AI Engineer job, you will be responsible for designing, developing and deploying AI-powered applications, working across backend services, data pipelines and intelligent workflows.
Using Python and Django, you will build scalable applications, develop AI agents, implement Retrieval-Augmented Generation (RAG) pipelines and integrate large language models (LLMs) with databases, APIs and existing business systems.
You'll need strong software engineering skills, practical AI experience and a proactive approach to problem-solving. You'll also have the opportunity to explore emerging technologies, improve system performance and help develop reliable, production-ready AI solutions in a fast-moving financial environment.
Key responsibilities - Full-Stack AI Engineer
In this Full-Stack AI Engineer job, your responsibilities will include:
- Developing AI applications: Building and maintaining scalable applications using Python, Django and RESTful APIs.
- Building agentic workflows: Developing AI agents that use tools, APIs and multi-step workflows to automate business processes.
- Integrating LLMs: Working with commercial and open-source language models, balancing accuracy, performance, latency and cost.
- Developing RAG systems: Building document ingestion, embedding, indexing and retrieval pipelines, including semantic search, metadata filtering and reranking.
- Managing data and integrations: Working with structured and unstructured data, SQL, NoSQL, vector databases and external services.
- Implementing AI tools: Developing tool-calling workflows and integrating Model Context Protocol (MCP) servers.
- Testing and optimisation: Evaluating AI accuracy, retrieval quality and reliability, and improving application performance.
- Supporting production systems: Using Docker, Git and GitHub to support testing, deployment, documentation and maintenance.
- Improving processes: Exploring new AI frameworks, improving architecture and identifying opportunities to make applications more efficient and reliable.
In this Full-Stack AI Engineer job, the ideal candidate will be:
- An experienced Python developer with backend development and REST API experience using Django, Django REST Framework, FastAPI or similar frameworks.
- Knowledgeable in object-oriented programming, SOLID principles, software architecture and design patterns.
- Experienced in integrating LLMs into applications and developing AI-powered workflows.
- Familiar with agentic AI, tool calling, function calling and LLM orchestration.
- Experienced in RAG, embeddings, vector indexing, semantic search and retrieval optimisation.
- Comfortable working with SQL, relational databases and structured and unstructured data.
- Familiar with Docker, Git, GitHub, automated testing and modern development practices.
- Analytical and proactive, with strong debugging skills and the ability to deliver reliable, maintainable production software.
It would also be beneficial if you have:
- Experience with MCP servers, multi-agent systems or advanced LLM orchestration.
- Familiarity with vector databases such as Qdrant, Pinecone, Weaviate or Chroma, and graph databases such as Neo4j.
- Knowledge of machine learning and NLP frameworks such as PyTorch, TensorFlow or scikit-learn.
- Experience with asynchronous processing, message brokers or distributed task queues.
- Exposure to OCR, document AI and information extraction from PDFs and spreadsheets.
- Familiarity with TypeScript, React, C#/.NET or Java.
- Experience with model fine-tuning, inference optimisation or deploying open-source LLMs.
- Experience in financial services, hedge funds, investment management or other data-intensive industries.
- Salary of £40,000 - £60,000 per annum.
- The opportunity to develop real-world AI applications within a hedge fund environment.
- Hands-on experience with LLMs, agentic
- Perfomance Bonus
- Private Medical
- Bonus opportunities
- Financial planning support
- Life insurance