ML & AI Engineer

Vallum Associates; Greater London; On-site; GBP 60,000 - 80,000; Full time

Job summary

A leading technology firm in Greater London is looking for a skilled AI Engineer to develop innovative AI products for the Conversational Banking Lab. The role involves creating infrastructure for agent workflows across Azure and GCP, and expertise in Python, AI Engineering, and microservices is essential. The ideal candidate should have experience in production-grade LLM applications and a solid understanding of CI/CD and event-driven architecture. This position offers a collaborative work environment focused on cutting-edge AI solutions.

Qualifications

• Must have at least 2 years of experience in Python-based LLM applications.
• Strong understanding of microservices and CI/CD pipelines is essential.
• Experience in AI engineering, including prompt engineering and RAG pipelines.

Responsibilities

• Develop infrastructure to support agentic workflows across Azure and GCP.
• Shape the design of Coach AI and AI Assistant solutions.
• Create agent integration patterns leveraging Bank systems.
• Develop new AI products for the Conversational Banking Lab.

Skills

Python literacy - min 2 years+ working on production grade LLM based applications

Strong understanding of microservices architecture

CI/CD pipelines

Event driven architecture

AI Engineering

RAG pipelines

Prompt engineering

VertexAI experience

LLMOps and runtime evaluation/monitoring

Job description

Developing and provisioning of infrastructure that support agentic workflows across both Azure and GCP

Data science expertise to help shape the agentic solution design of Coach AI as well as target state AI Assistant

Creation of agent integration patterns to fulfil and action on behalf of customers by leveraging Bank systems

Development of new AI products for the Conversational Banking Lab, including but not limited to:

• Agent summarisation - bespoke features to summarise nuanced conversations
• App search evolution - transforming the existing vector search functionality into a fully generative experience and transition to single experience point
• Evaluation methods - continued automation of both deterministic and generative conversations in a scaled and simulated way

Must haves

• 1. Python literacy - min 2years+ working on production grade LLM based applications
• 2. Software Engineering - strong understanding of microservices architecture, CI/CD pipelines, event driven architecture
• 3. AI Engineering - RAG pipelines, prompt engineering, VertexAI experience, LLMOps and runtime evaluation/monitoring

Nice to haves

• 1. AgenticAI - Langgraph, ADK, CrewAI, multi-agent architectures - experience in building deployable solutions, not jupyter notebooks
• 2. Data ontologies - graphical approaches to data storage + retrieval
• • Exposure to Agile/Scrum methodologies.