Applied AI Architect
Version 1 · Dublin
Company Description
Version 1 has celebrated 30 years in business and continues to be trusted by global brands to deliver technology and transformation solutions that drive customer success. Our deep expertise enables our customers to navigate the rapidly evolving technology landscape. We foster strong partnerships with global technology leaders including Microsoft, AWS, Oracle, Red Hat, OutSystems, Snowflake, ensuring that our customers are provided with the highest quality solutions and services.
We’re an award-winning employer reflecting how our employees are at the very heart of what we do:
UK & Ireland's premier AWS, Microsoft & Oracle partner
4000+ strong, €450/£400m revenue business
10+ years as a Great Place to Work in Ireland & UK
Best Workplace for Women in the UK & Ireland by GPTW
Best Workplace for Wellbeing in the UK by GPTW
We’re a core values driven company, we hire people who share our values, and we reward those who display and foster them, it’s deeply embedded within our DNA. Invest in us and we’ll invest in you!
Job Description
AI is the biggest shift in how organisations build and work in a generation. The organisations who win will be the ones who can move beyond a working demo and get genuinely production-grade, multi-agent AI systems live, reliable and maintained at scale. That is the hardest part of the journey, and it's where this role sits.
As an Applied AI Architect working in Version 1's Forward Deployed capability, you bring deep, hands-on expertise in designing, building, deploying and maintaining agentic systems in production, and you bring it to customers as a trusted adviser, not from behind a desk. You've done this for real — not just prototyped an agent, but taken a multi-agent architecture through the full lifecycle: design, orchestration, evaluation, deployment, and the unglamorous work of keeping it reliable once real users depend on it. You sit alongside customer architects and senior engineers, on their most technically demanding challenges, combining deep technical credibility with genuine consulting skill to shape decisions rather than simply hand over a design.
This is a deeply technical role that lives in the room with the customer. You'll set the technical standard for Version 1's most complex agentic engagements, and you'll do it through influence and trust as much as through the strength of your own architecture.
What you'll do
Advise the customer's own AI architects. Act as the trusted technical adviser to the customer's AI architect and senior engineers, shaping their design and build decisions on agentic systems rather than owning delivery yourself.
Consult across the engagement. Run discovery, workshops and architecture reviews with customer stakeholders, translating technical trade-offs into language that lands with both engineers and the business sponsors funding the work.
Architect multi-agent systems, hands-on. Work directly with customer engineering teams to co-design multi-agent architectures — orchestration, tool use, memory, routing and guardrails — for real production workloads.
Build reference implementations and accelerators. Create working prototypes, reference architectures, evaluation suites and accelerator code that customer teams take on and run themselves — proof that survives contact with production, not slideware.
Solve the hard production problems. Bring deep experience of what breaks agentic systems at scale — hallucination under load, tool-call failures, runaway agent loops, latency and cost — and help customer teams design around it.
Set the technical bar for the engagement. Own the technical architecture and standards for Version 1's most complex agentic engagements, reviewing and pressure-testing customer designs as a peer to their best architects.
Own evaluation and observability. Establish how a customer will know their agentic system is actually working — eval suites, tracing, guardrails and monitoring — before it goes anywhere near production.
Mentor on deep technical practice. Coach Applied AI Consultants and Associates on advanced AI engineering, sharing hands-on expertise that goes well beyond the basics.
Build Version 1's technical IP. Contribute reusable architectures, patterns and accelerators to Version 1's shared toolkit, keeping it current with the frontier of agentic AI engineering.
Stay genuinely current. Track the latest agent frameworks, orchestration patterns and models closely enough to have a real, tested opinion on what's worth using and what isn't.
Qualifications
What good looks like
Proven agentic systems experience. You've personally designed, built, deployed and maintained multi-agent systems in production — not a hackathon demo, a system real users depended on.
A genuine consultant, not just an engineer. You build trust quickly with customer stakeholders, read a room, and flex your style between hands-on engineers and the people funding the work — this role lives in front of the customer, not behind a laptop.
Deep architectural credibility. You can design and defend a multi-agent architecture — orchestration patterns, tool permissions, routing logic, guardrails — under scrutiny from a customer's best engineers.
Genuinely current technical depth. Your expertise in LLMs, agent frameworks and evaluation is real and current, built through hands-on production work, not reading about it.
Comfortable in the hardest part of the job. You know that the interesting problems in agentic AI start after the demo works, and you're energised by solving them.
A builder who can advise, not just build. You'd rather be pairing on an architecture or debugging an agent trace than sitting in a status meeting, but you're just as effective guiding someone else's team to the right answer as reaching it yourself.
What we're looking for
10–15+ years in software engineering, including 5+ years designing and architecting systems.
A minimum of 2 years' hands-on experience architecting and running AI/agentic systems in production.
A genuine track record of client-facing or consulting work, advising engineering teams or technical stakeholders rather than only delivering internally.
Direct experience designing multi-agent architectures: orchestration, tool use, memory, routing, guardrails and agent-to-agent communication.
Production experience with agent frameworks such as LangGraph, Microsoft Foundry, AWS Bedrock, CrewAI, AutoGen, or comparable orchestration tooling, plus MCP or similar protocols.
Strong grounding in evaluation, observability and reliability for AI systems: eval suites, tracing, guardrails, monitoring and incident response for agentic workloads.
Hands-on experience with the Claude API, Claude Code, MCP, GitHub's AI tooling, or equivalent leading AI platforms and tooling, in production.
A degree in a related field, or equivalent practical experience.
What Version 1 gives you
A role built around the craft, in front of the customer. This track exists for people who want to stay deeply technical at the most senior level, advising and shaping rather than managing, without disappearing from client conversations.
The hardest, most interesting problems. You'll work on the agentic systems our most demanding customers are betting their operations on, at a stage of maturity most engineers never get to touch.
Real technical authority. You'll set the standard the rest of the team builds towards, earned through trust with customers as much as through the strength of your architecture.
Additional Information
Why Version 1?
At Version 1, we believe in providing our employees with a comprehensive benefits package that prioritises their wellbeing, professional growth, and financial stability.
Share in our success with our Quarterly Performance-Related Profit Share Scheme, where employees collectively benefit from a share of our company's profits
Strong Career Progression & mentorship coaching through our Strength in Balance & Leadership schemes with a dedicated quarterly Pathways Career Development programme
Flexible/remote working, Version 1 is tremendously understanding of life events and people’s individual circumstances and offer flexibility to help achieve a healthy work life balance
Financial Wellbeing initiatives including; Pension, Private Healthcare Cover, Life Assurance, Financial advice and an Employee Discount scheme
Employee Wellbeing schemes including Gym Discounts, Bike to Work, Fitness classes, Mindfulness Workshops, Employee Assistance Programme and much more. Generous holiday allowance, enhanced maternity/paternity leave, marriage/civil partnership leave and special leave policies
Educational assistance, incentivised certifications, and accreditations, including AWS, Microsoft, Oracle, and Red Hat
Reward schemes including Version 1’s Annual Excellence Awards & ‘Call-Out’ platform.
Environment, Social and Community First initiatives allow you to get involved in local fundraising and development opportunities as part of fostering our diversity, inclusion and belonging schemes.
Version 1 is an equal opportunities employer.
We are committed to building a diverse, inclusive and respectful workplace where everyone feels valued and able to thrive. We welcome applications from people of all backgrounds, identities and lived experiences, and we value the different perspectives people bring including those shaped by disability and neurodiversity.
Our employee-designed Profit Share scheme divides a portion of our company's profits each quarter amongst employees. We are dedicated to helping our employees reach their full potential, offering Pathways Career Development Quarterly, a programme designed to support professional growth.