Senior AI Engineer | Tech | UK in London

Join Savanta as a Senior AI Engineer and play a key role in shaping how AI powers our products, platforms and internal tools.

About Us: Savanta is a leading data, market research and advisory company helping the world's leading brands make better decisions, faster. With over 500 people across offices in multiple countries, we combine deep research expertise, proprietary technology and high-impact consulting to give our clients a complete view of their markets, their customers and their competitors. Our platform gives clients access to over 100 million respondents globally, alongside a suite of intelligence products covering brand tracking, market monitoring, consumer trends, and AI-powered insight delivery. We work with leading organisations across financial services, retail, CPG, media, technology and the public sector.

About the Role: This is a hands-on opportunity for an experienced engineer who enjoys building production-grade AI applications, turning complex business challenges into practical, scalable solutions. You’ll work with C#/.NET, Azure and modern LLM technologies to create intelligent features that deliver real impact for users and the business. This is an exciting opportunity to join Savanta at a time when AI is becoming a core part of both our client offering and internal technology roadmap. Your work will have visible impact quickly, with the chance to ship meaningful AI-enabled products in short iterations, learn from real usage and continuously improve quality. You’ll collaborate with product, engineering, QA, UX and business stakeholders, while also helping to raise AI engineering capability across the wider technology team through coaching, practical standards and technical leadership.

Some of the key areas you will work on:

• Making sound engineering calls on prompt design, tool use, structured outputs, orchestration, guardrails and fallback behaviour.
• Designing LLM-powered systems with grounding techniques like RAG, search tools and knowledge graphs.
• Defining and running LLM evaluations - factuality, grounding, instruction following, schema adherence, safety and task success.
• Shipping AI-powered features such as chat, summarisation, extraction, classification, workflow copilots and retrieval-backed assistants.

Our Tech Team works within a learning and collaborative environment, where empowerment is key to our success, along with developing a culture of innovation and creating an environment where everyone can excel. Our development teams have a lot of autonomy in how to work day-to-day, with support from other roles as needed.

Our tech stack includes:

• .NET / C#, including APIs and backend services
• Microsoft Azure, including cloud-native services for AI workloads
• LLM application patterns, including prompt orchestration, retrieval pipelines, and evaluation
• OpenAI-compatible APIs / SDKs and related tooling
• GitHub / Azure DevOps CI/CD pipelines
• Data platforms and storage services, including structured and unstructured data handling

About You: We’re looking for someone who combines excellent software engineering fundamentals with strong numerical confidence, clear communication skills and the ability to work effectively with both technical and non-technical stakeholders. You’ll bring strong experience in C# and .NET, along with a proven track record of building and deploying cloud-based applications in Azure. You should have hands-on experience delivering LLM-powered applications in production, with a solid understanding of prompt orchestration, retrieval-augmented generation, vector embeddings, evaluation and AI-specific testing. Experience mentoring others, improving engineering standards and balancing speed, safety, cost and quality in AI delivery will also be highly valued.

Essential Experience:

• Strong ability in C# and .NET building production applications and services.
• Writing and using unit tests, using any language and test framework.
• Microsoft Azure and deploying cloud-based applications in production environments.
• Hands-on experience implementing LLM-driven applications beyond experimentation or demos.
• Able to explain and apply LLM evals as a core quality discipline for AI applications.
• Familiarity with OpenAI-compatible APIs, protocols, or SDKs, and the practical considerations of integrating them into applications.
• Clear understanding of RAG and the role of vector embeddings in retrieval-based AI systems.
• Strong understanding of software testing fundamentals, including unit, integration, and end-to-end testing, and how these differ from AI-specific evaluation.
• Numerical confidence and working familiarity with concepts such as similarity, clustering, PCA, and basic linear algebra.
• Full product delivery mindset focused on user value, reliability, and measurable quality.
• Comfortable working with ambiguity, rapid iteration, and shifting priorities.
• Strong communication skills and ability to work effectively with technical and non-technical stakeholders.

Desirable Experience:

• Using or building RAG systems in production, including retrieval tuning and relevance evaluation.
• Vector databases or Azure-native retrieval/search services.
• Working with Snowflake or other data warehouses.
• Working with SQL Server.
• Using Azure AI services, model hosting platforms, or related observability tooling.
• Prompt management, structured output validation, tool calling, or agent-style workflows.
• Defining evaluation datasets, benchmark suites, and regression testing pipelines for LLM applications.
• Exposure to broader ML concepts or workflows beyond LLMs.
• Mentoring other engineers and helping establish AI engineering standards.
• Security, privacy, and governance considerations for enterprise AI solutions.

And in return, Savanta offers:

• Salary range: £60,000 - £70,000
• Bonus scheme
• Unlimited annual leave
• Remote Working (only required onsite 1-2 days per month)
• Employee Assistance Program
• Flexible working practices
• Health & wellbeing package
• Ongoing Learning & Development
• Financial health (pension, life assurance, etc.)
• Team & Company Socials
• Committees for Health & Well Being, Charities & Volunteering and DE&I

Why Join Us: The company was founded on the belief that tech should be integral to its success, and this culture of tech innovation makes us best placed to put Savanta at the heart of our clients’ businesses offering solutions before they even know the problem. Part of the vibrant Next 15 Communications Group, we have an entrepreneurial and inclusive company culture that actively recognizes and values its people and offers unrivalled scope for career development, including mentoring, coaching as well as extensive training programs. Savanta is committed to being an equal opportunities employer and continuously strives to be an employer of choice. Our people are our greatest asset - we value workplace diversity and inclusion, oppose all forms of unlawful discrimination, and welcome applications from suitably qualified candidates of all backgrounds. All candidates will be considered equally, however, unfortunately we are unable to offer visa sponsorship. We encourage authentic responses to demonstrate your experience and approach, rather than relying on Generative AI tools to write your cover letter or any questions in the application process. We may use AI Decoders as part of the review process and if answers match to a high extent that may be factored into the review.