AI Engineer (Agentic/Generative)

AI Engineer (Agentic/Generative)

Hybrid Working - London - 2 days a week on site.

Financial Services

Lorien's leading banking client is looking for an exceptional AI Engineer with strong experience in Agentic AI, Generative AI, and applied machine learning to design, build, and deploy intelligent systems at scale.

In this role, you'll lead the development of multi-agent architectures that analyse campaigns, creative content, brand perception, and social media impact, while also working on Generative AI and RAG-based solutions that connect natural language interfaces to complex data sources. You'll collaborate closely with Data Scientists, ML Engineers, and stakeholders to turn advanced AI concepts into robust, production-ready systems.

This is a hands-on technical role with real ownership, combining architecture, engineering, and leadership.

This role is based in London.

This role will be Via Umbrella.

Working in a Hybrid Model of 2 days a week on site.

What You'll Do

• Design, build, and deploy agentic AI systems using multi-agent architectures.
• Lead the development of Generative AI and Retrieval Augmented Generation (RAG) pipelines.
• Build specialised agents for tasks such as campaign analysis, creative strategy evaluation, budget optimization, and influencer assessment.
• Prototype solutions using tools such as LangChain and LangGraph, and harden them with OpenAI's native Agents SDK.
• Implement secure agent orchestration, structured outputs, function calling, and observability (logging, tracing, monitoring).
• Containerise services using Docker and deploy scalable solutions on Azure, AWS, or GCP.
• Work with vector databases (eg Pinecone) and evaluate similarity metrics for semantic search.
• Collaborate with cross-functional teams to translate business needs into AI-driven solutions.
• Own technical documentation, architectural decisions, and development standards.
• Support CI/CD pipelines, model monitoring, drift detection, and retraining strategies.

Essential Skills & Experience

• Strong experience in Python and ML/AI engineering.
• Hands-on expertise with Large Language Models (OpenAI GPT-3.5, GPT-4, and similar).
• Proven experience building RAG pipelines, semantic search, and NLP-based systems.
• Experience with agentic frameworks (Agents SDK, LangChain, LangGraph).
• Solid ML foundations: classification, clustering, forecasting, and optimisation.
• Experience with containerization and cloud deployment (Docker, Kubernetes, Azure/AWS/GCP).
• Familiarity with MLOps practices: CI/CD, monitoring, model drift, versioning.
• Strong data skills using SQL, Pandas, NumPy, and visualisation tools.

Tech Stack Snapshot

• Languages: Python, SQL (plus R, C/C++, Java beneficial)
• ML/AI: TensorFlow, PyTorch, Keras, Scikit-Learn
• Generative AI: OpenAI, Anthropic, Llama, RAG, Prompt Engineering
• Data & Storage: PostgreSQL, Redshift, MongoDB, DynamoDB
• Cloud & DevOps: Azure, AWS, GCP, Docker, Kubernetes, CI/CD
• Monitoring: Helicone, cloud-native observability tools

IND_PC3

Guidant, Carbon60, Lorien & SRG - The Impellam Group Portfolio are acting as an Employment Business in relation to this vacancy.