GenAI Engineer in London

About Klarus

Klarus is a global, senior-led AI consultancy delivering technology-enabled transformation and measurable business impact. We partner with boards and executive teams navigating complex operating model change, digital transformation, and responsible AI adoption.

Our focus is not advisory theory but execution with accountability. We combine deep sector expertise with hands-on transformation leadership and agentic AI to shape value cases, redesign operating models, strengthen governance, and embed scalable digital and AI capability. The result is reduced risk, accelerated delivery and technology investment that translates into durable enterprise outcomes.

If you are ambitious, growth-oriented and excited by the opportunity to help build a next-generation consulting firm while delivering meaningful transformation for clients, Klarus offers a genuinely compelling career trajectory.

Role Summary

As a GenAI Engineer, you will design, build and scale the next generation of agentic AI capabilities across our consulting and client environments. This is a hands-on technical role that blends systems architecture, agent design, applied LLM engineering, and enabling others through frameworks, education and tooling. You will work closely with our AI strategy, data, and delivery teams to embed GenAI safely and effectively across multiple use cases.

Key Responsibilities

• Environment & Architecture Set-Up
  • Design, configure and manage secure GenAI development environments (Azure, AWS, GCP, or hybrid).
  • Design and implement agent orchestration architectures using frameworks such as LangChain, LlamaIndex, Semantic Kernel, AutoGen, or custom event-driven systems.
  • Integrate with enterprise systems, APIs, data stores and operational tooling.
  • Establish governance frameworks covering PII detection and minimisation, retention and deletion policies for embeddings/state, audit logging, and alignment to client compliance requirements (e.g., GDPR, SOC2/ISO27001 where applicable).
• Bespoke AI Agent Creation
  • Build custom domain-specific agents using OpenAI, Claude, Gemini or other LLM providers.
  • Design multi-step agent workflows, toolchains and action schemas for complex reasoning and execution.
  • Design and optimise short-term and long-term memory systems including vector-based retrieval memory, conversation state management, and external persistence layers.
  • Prototype, test and productionise agents for internal teams and external client projects.
• Framework & Standards Development
  • Create reusable frameworks, patterns and templates for agent development (e.g., prompt libraries, tool adapters, orchestration patterns, evaluation frameworks).
  • Establish coding standards, model evaluation criteria and agent lifecycle guidelines.
  • Build self-service components that enable consultants and engineers to develop agents safely and consistently.
  • Document architecture, best practices and technical decision-making.
• Education, Enablement & Training
  • Deliver training sessions to consultants, engineers and client teams on building and using GenAI agents.
  • Produce clear guides, playbooks and learning modules for non-technical users.
  • Mentor junior engineers and act as a subject-matter expert on LLM technologies and agentic patterns.
• Experimentation, Evaluation & Improvement
  • Run experiments across model types, prompting approaches, RAG strategies and agent coordination methods.
  • Evaluate models for performance, cost, safety and reliability.
  • Contribute to continuous improvement of internal AI tooling, pipelines and architecture.

Skills & Experience

• Technical
  • Strong hands-on experience delivering production LLM systems using major providers (OpenAI, Anthropic, Google).
  • Proficiency in Python or JavaScript/TypeScript for agent logic, tool integration and orchestration.
  • Experience with vector databases (Pinecone, Chroma, Weaviate, Redis, etc.).
  • Solid understanding of RAG pipelines, embeddings, prompt engineering and LLM evaluation.
  • Familiarity with containerisation, CI/CD, cloud security, and API integration.
  • Experience deploying GenAI applications into production environments (e.g. latency optimization, caching strategies, rate limiting, concurrency management, streaming responses, and cost controls).
• Consulting / Delivery
  • Ability to translate business requirements into technical AI solutions.
  • Strong communication skills, especially in explaining GenAI concepts to non-technical audiences.
  • Experience working in client-facing or cross-functional project teams.