Senior AI Engineer

Publicis Media; Greater London; Hybrid; GBP 55,000 - 95,000; Full time

Benefits offered by this job

Healthcare

Life Assurance

Pension

Job summary

Profitero+, now part of Publicis Groupe, seeks an experienced AI/ML backend engineer to design, develop, and deploy LLM-based systems and agentic AI workflows. This hybrid role spans Reading and London, offering flexible hours and a competitive package.

Candidates should have a Bachelors or Masters in CS/Engineering/AI, 3+ years in software development with AI/ML focus, strong Python skills, and experience with LLMs, RAG, embeddings, MCP, and API integrations.

Qualifications

• Degree in CS/Engineering/AI or related field.
• 3+ years of software development with AI/ML focus.
• Proficiency in Python and AI/ML libraries/frameworks.

Responsibilities

• Design, develop, and deploy LLM-based systems and agentic AI workflows.
• Operate and iterate AI systems in production with performance tuning and cost optimization.
• Build Retrieval-Augmented Generation (RAG) systems using embeddings and vector databases.
• Develop robust Python backend code for API integrations and services.
• Collaborate with product managers and engineers to translate requirements.

Skills

Python

AI/ML

RESTful APIs

Git

CI/CD

Communication

Education

Bachelor's or Master's in Computer Science/Engineering/AI

Job description

Salary: £55,000 - 95,000 per year

Requirements:

• We require a Bachelors or Masters degree in Computer Science, Engineering, Artificial Intelligence, or a related field.
• We require a minimum of 3 years of professional experience in software development, with a significant focus on AI/ML applications.
• We require proven proficiency in Python and experience with relevant AI/ML libraries and frameworks.
• We require hands-on experience developing applications utilizing Large Language Models (LLMs) such as Claude, OpenAI GPT-4, Google Gemini, or similar generative AI models.
• We require experience building agentic applications or workflows, including planning, memory, tool usage, and multi-agent systems.
• We require familiarity with AI workflow orchestration and agentic frameworks such as LangChain, LangGraph, Crew AI, Haystack, or similar.
• We require practical experience with RAG architectures, embeddings, vector databases, and semantic search.
• We require experience working with Model Context Protocol (MCP) Servers.
• We require experience with RESTful APIs and integrating external services.
• We require a solid understanding of software development best practices, including version control (Git), testing, and CI/CD.
• We prefer experience with Snowflake.
• We require excellent problem-solving skills and the ability to work independently and as part of a collaborative team.
• We require strong communication skills, both written and verbal.

Responsibilities:

• We design, develop, and deploy LLM-based systems, agentic applications, and complex AI workflows using generative AI models and relevant frameworks.
• We deploy, operate, and iterate on AI systems in production environments, including performance tuning and cost optimization.
• We design and build Retrieval-Augmented Generation (RAG) systems using embeddings, vector databases, and semantic search.
• We build and optimize prompts and interaction strategies for LLMs to achieve desired outcomes in agentic systems.
• We integrate various tools, APIs, and data sources, potentially utilizing MCP Servers, to enhance model context and tool integration.
• We develop robust, scalable, and maintainable Python code for backend logic and API integrations.
• We implement testing, evaluation, and monitoring strategies to ensure performance, reliability, safety, effective reasoning, tool usage, and failure handling.
• We collaborate closely with product managers, designers, and other engineers to translate requirements into technical solutions.
• We stay up to date with the latest research and developments in generative AI, LLMs, agentic systems, and protocols like MCP, evaluating their potential for our products.
• We contribute to the architecture and technical roadmap of our AI initiatives.
• We mentor junior engineers and share knowledge within the team.
• We undertake such duties as may reasonably be requested within the scope of the post.

Technologies:

• AI
• API
• Backend
• CI/CD
• Git
• LLM
• MCP
• Python
• RAG
• Snowflake
• Agentic AI
• Marketing

More:

We are Profitero+, a leading global SaaS commerce platform using predictive intelligence to help brands anticipate, activate, and automate their next best action for profitable growth. Our technology monitors 80+ million products daily across 1,400 retailers and 70+ countries, supporting brands with search placement, product content, pricing, stock availability, reviews, and more. We are now part of Publicis Groupe as a standalone commerce division, giving us significant product development resources and investment while offering our employees a strong launchpad for their careers.

This is a hybrid role based in Reading and London, with flexible working hours, and we are unable to provide sponsorship for this vacancy. We offer a competitive package including base salary, healthcare, life assurance, group income protection, dental care, eye care, 24-hour online GP, company pension, cycle to work scheme, 25 days off plus bank holidays and birthdays off, reduced gym membership, social events, employee referral scheme, personal development plans, and our Profitero Hero scheme. We are committed to a diverse and inclusive work environment and are proud to be an equal opportunity employer.