Job Description

Technology is our how. And people are our why. For over two decades, we have been harnessing technology to drive meaningful change.

By combining world-class engineering, industry expertise and a people-centric mindset, we consult and partner with leading brands from various industries to create dynamic platforms and intelligent digital experiences that drive innovation and transform businesses.

From prototype to real-world impact - be part of a global shift by doing work that matters.

We are looking for a highly skilled and hands-on AI Architect to design and lead the implementation of multi-agent (agentic) systems in enterprise environments.

This is not a prompt engineering or chatbot role. We are focused on building production-grade AI systems, where multiple agents collaborate, reason, and execute complex workflows integrated with real business processes.

Key Responsibilities

• Design multi-agent architectures (task decomposition, orchestration, coordination patterns)

• Define how LLM-powered agents interact with:

• Enterprise data platforms

• APIs and tools

• Operational workflows

• Lead agentic systems from PoC to production with model, cost, security, privacy, and responsible AI guardrails

• Establish observability, tracing, feedback loops, and controls for agent behavior

• Define memory strategies (short-term, long-term, contextual grounding)

• Collaborate with data, platform, and engineering teams to integrate AI into core systems

• Guide and train teams on best practices for scalable and reliable AI systems

Qualifications

What We’re Looking For

Core Experience

• Strong background in software architecture and distributed systems

• Hands-on experience building complex LLM-based applications

• Experience designing complex workflows or orchestration systems

• Solid understanding of RAG architectures, retrieval optimization, and retrieval quality

LLM & AI Foundations

• Strong understanding of Large Language Model (LLM) fundamentals, not just usage

• Solid grasp of Transformer architecture (attention mechanisms, embeddings, tokenization)

• Understanding of how LLMs are trained and behave:

• Pretraining vs fine-tuning vs instruction tuning

• Context windows and limitations

• Hallucinations and mitigation strategies

• Familiarity with NLP concepts:

• Semantic similarity

• Text embeddings and vector representations

• Information retrieval principles

• Ability to reason about model behavior and limitations, not treat LLMs as black boxes

Agentic / AI-Specific

• Experience with multi-agent frameworks (LangChain, Semantic Kernel, Agent Framework, CrewAI, or custom)

• Experience on platforms for managing the lifecycle of generative AI applications and agents like Amazon Bedrock (AWS), Google Vertex AI (GCP) or Azure AI Foundry

• Familiarity with protocols like: MCP, UCP, A2A, AP2

• Familiarity with:

• Tool use / function calling

• Agent coordination patterns

• Memory and context management

• Experience evaluating and improving LLM reliability and accuracy

Engineering & Platform

• Cloud experience (AWS, Azure, or GCP)

• Strong coding skills (Python preferred)

• Experience integrating AI with enterprise systems (APIs, data platforms, event-driven systems)

What Makes This Role Different

• Focus on systems, not isolated models

• Real enterprise use cases, not experimental demos

• Opportunity to define architecture patterns for agentic systems

• Work at the intersection of AI, data, and distributed systems

Additional Information

Discover some of the global benefits that empower our people to become the best version of themselves:

• Finance: Competitive salary package, share plan, company performance bonuses, value-based recognition awards, referral bonus;
• Career Development: Career coaching, global career opportunities, non-linear career paths, internal development programmes for management and technical leadership;
• Learning Opportunities: Complex projects, rotations, internal tech communities, training, certifications, coaching, online learning platforms subscriptions, pass-it-on sessions, workshops, conferences;
• Work-Life Balance: Hybrid work and flexible working hours, employee assistance programme;
• Health: Global internal wellbeing programme, access to wellbeing apps;
• Community: Global internal tech communities, hobby clubs and interest groups, inclusion and diversity programmes, events and celebrations.

At Endava, we’re committed to creating an open, inclusive, and respectful environment where everyone feels safe, valued, and empowered to be their best. We welcome applications from people of all backgrounds, experiences, and perspectives—because we know that inclusive teams help us deliver smarter, more innovative solutions for our customers. Hiring decisions are based on merit, skills, qualifications, and potential. If you need adjustments or support during the recruitment process, please let us know.