Applied AI Software Engineer

Hybrid - Full time

Bristol, England, United Kingdom

Role and Responsibilities

We are looking for a skilled Python developer with proven experience in building applications and integrating modern generative AI models. This role is ideal for someone who thrives in a fast-paced, dynamic environment. You’ll be working in a collaborative, creative, and small-scale production team where agility and adaptability are key.

Your responsibilities will include:

• Leveraging cutting-edge AI technologies to solve real-world customer challenges.
• Collaborating with product teams to translate business and product requirements into advanced AI-driven solutions.
• Designing and developing intelligent AI agents and multi-agent systems capable of autonomous decision-making, complex workflows, and real-time problem-solving.
• Implementing agent-based architectures for applications like task orchestration, adaptive learning, and dynamic data analysis.
• Building and deploying Retrieval-Augmented Generation (RAG) systems to enhance contextual response accuracy in AI models.
• Optimizing generative model outputs through advanced prompt engineering strategies for diverse use cases.

Work Location
United Kingdom

Experience and Qualifications

Essential Requirements:

• Solid foundation in professional software engineering with approximately 5+ years of industry experience.
• Expertise in Python, with hands-on, production-level experience.
• Proficiency in modern software engineering practices, including test-driven development, version control, CI/CD pipelines, and containerization.
• Practical experience building applications and integrating generative AI models (e.g., LLMs).
• Proven ability to optimize generative model outputs using advanced techniques.
• Strong analytical and problem-solving skills.
• Ability to work both independently and collaboratively in a dynamic, fast-moving environment.

Preferred Qualifications:

• Strong knowledge of AI/ML principles, focusing on Generative AI and Large Language Models (LLMs).
• Understanding the trade-offs, capabilities, and limitations of various AI models.
• Experience with vector embeddings and vector databases (e.g., Pinecone).
• Hands-on experience with RAG techniques, fine-tuning pre-trained models, and tools like LangChain, LlamaIndex, Hugging Face, AWS Bedrock, or Google Vertex AI.
• Familiarity with at least one major cloud platform (AWS, GCP, or Azure).
• Knowledge of MLOps/LLMOps practices, including deployment, serving, and monitoring AI models.
• Experience in data engineering and managing data pipelines for AI applications.

What We Offer:

• Flexibility: Option for contract or full-time employment.
• Competitive compensation.
• Hybrid working arrangements and a conveniently located office in Bristol, within 5–10 minutes of major train and bus routes.
• An opportunity to be part of a fast-paced, highly ambitious team.