Senior Applied AI Engineer – Gen & Agentic AI
TechJobs.ie Job Insights
At a glance
Technologies & skills
What you'll be doing
Join a global AI Innovation and R&D team as a Senior Applied AI Engineer, focusing on building production-ready Generative and Agentic AI systems. This hands-on role involves designing, building, and operating advanced AI systems with an emphasis on reliability, scalability, and production readiness.
- Design, build, and own production-grade agentic AI systems end-to-end
- Develop stateful and reliable agent workflows, including planning, tool usage, memory, and human-in-the-loop controls
- Implement advanced retrieval and grounding techniques such as hybrid search, reranking, and contextual assembly
- Build secure tool integrations and expose internal and external services for agent consumption
- Treat AI evaluation as an engineering discipline using regression testing, metrics, and release gates
- Implement LLMOps and AgentOps practices to monitor cost, latency, quality, and system performance
- Optimise AI systems for performance, reliability, and cost efficiency across models and providers
- Build and operate backend services, including Python APIs, workflow orchestration, and event-driven systems
Key requirements
Must-have
- 6+ years of experience in software engineering, applied machine learning, or applied AI
- Strong Python development skills with solid software engineering fundamentals
- Proven experience building and deploying LLM-powered applications in production
- Hands-on experience with agentic frameworks such as LangChain, LlamaIndex, LangGraph, CrewAI, or similar
- Strong understanding of retrieval systems and vector databases
- Familiarity with agent design patterns including planning, tool use, ReAct, and multi-agent systems
- Experience deploying and operating production systems on cloud platforms such as AWS, Azure, or GCP
- Comfortable working with Docker, CI/CD pipelines, and production environments
Experience: 6+ years
Role signals
- Technical focus
- AI systems, agentic workflows, production engineering
- Architecture / system design
- Indicated in the listing
- Hands-on vs management
- Hands-on
Similar jobs
Check your CV against this job
Get a certified technical review aimed at this role.
Full job description
Senior Applied AI Engineer – Generative & Agentic AI
- €100-112K + Bonus + Bens
- An exciting opportunity for a Senior Applied AI Engineer to join a global AI Innovation and R&D team focused on building production-ready Generative and Agentic AI systems.
- This is a hands-on engineering role suited to someone who enjoys delivering real-world AI products and working at the intersection of software engineering, agentic workflows, and applied GenAI.
The Role
You will design, build, and operate advanced AI systems end-to-end, with a strong focus on reliability, scalability, and production readiness.
- Design, build, and own production-grade agentic AI systems end-to-end
- Develop stateful and reliable agent workflows, including planning, tool usage, memory, and human-in-the-loop controls
- Implement advanced retrieval and grounding techniques such as hybrid search, reranking, and contextual assembly
- Build secure tool integrations and expose internal and external services for agent consumption
- Treat AI evaluation as an engineering discipline using regression testing, metrics, and release gates
- Implement LLMOps and AgentOps practices to monitor cost, latency, quality, and system performance
- Optimise AI systems for performance, reliability, and cost efficiency across models and providers
- Build and operate backend services, including Python APIs, workflow orchestration, and event-driven systems
- Collaborate with data science, backend, and delivery teams to deliver scalable AI solutions
- Contribute to reusable components, technical documentation, and ongoing AI innovation initiatives
Experience & Skills
- 6+ years of experience in software engineering, applied machine learning, or applied AI
- Strong Python development skills with solid software engineering fundamentals
- Proven experience building and deploying LLM-powered applications in production
- Hands-on experience with agentic frameworks such as LangChain, LlamaIndex, LangGraph, CrewAI, or similar
- Strong understanding of retrieval systems and vector databases
- Familiarity with agent design patterns including planning, tool use, ReAct, and multi-agent systems
- Experience deploying and operating production systems on cloud platforms such as AWS, Azure, or GCP
- Comfortable working with Docker, CI/CD pipelines, and production environments
- Strong delivery mindset with a focus on building high-quality, reliable AI systems
- Must have Irish/EU Citizenship and be based within a commutable distance to Dublin
#LI-JM2
Interview prep pack
Grounded in this listing. Use it to prepare examples before you apply.
Your interview focus
Based on this listing, the Senior Applied AI Engineer role focuses on designing, building, and operating production-ready generative and agentic AI systems, with an emphasis on reliability, scalability, and hands-on engineering using Python and modern AI frameworks.
- Hands-on production engineering·High
- Agentic AI frameworks expertise·High
- Retrieval and vector database knowledge·High
- Cloud and DevOps for AI·Medium
Only have 30 minutes?
Follow a focused preparation plan based on this job.
Start 30-minute prep
Your 30-minute plan
Review and Summarize Recent Agentic AI Projects
0–8 minPrepare concise summaries of your most relevant projects, focusing on agentic workflows, production deployment, and outcomes.
Refresh Technical Knowledge on Retrieval and Vector Databases
8–15 minStudy advanced retrieval techniques, hybrid search, and vector database integration in LLM applications.
Practice Explaining LLMOps and AgentOps Strategies
15–20 minRehearse how you monitor, evaluate, and optimize AI systems for cost, latency, and reliability.
Prepare Cloud Deployment and DevOps Examples
20–25 minSelect and outline examples of deploying AI systems on AWS, Azure, or GCP, including Docker and CI/CD usage.
Draft Targeted Questions for the Interview
25–30 minWrite down 5-6 thoughtful questions about the team's challenges, processes, and technology stack.
Talking points
, 5 itemsEnd-to-End Development of Agentic AI Systems
You should be able to discuss your experience designing, building, and maintaining complex AI systems, highlighting your ownership of the full lifecycle from architecture to deployment.
Hands-on Experience with Agentic Frameworks (e.g., LangChain, LlamaIndex)
Prepare to give concrete examples of how you have used these frameworks to implement agent workflows, tool integrations, or multi-agent systems in production.
Advanced Retrieval and Grounding Techniques
Demonstrate your understanding of hybrid search, reranking, contextual assembly, and vector databases by describing relevant projects or solutions you have built.
LLMOps and AgentOps Practices
Be ready to explain how you have monitored, evaluated, and optimized AI systems for cost, latency, quality, and reliability using engineering best practices.
Cloud Deployment and DevOps for AI
Showcase your experience deploying and operating AI systems on AWS, Azure, or GCP, and your proficiency with Docker and CI/CD pipelines.
What to research
, 4 itemsReview Agentic AI Frameworks (LangChain, LlamaIndex, etc.)
Refresh your knowledge and hands-on experience with agentic frameworks, focusing on their use in production environments.
Deepen Understanding of Retrieval Systems and Vector Databases
Study advanced retrieval techniques, hybrid search, reranking, and the use of vector databases in AI applications.
Cloud Deployment and DevOps Practices
Prepare examples of deploying and operating AI systems on AWS, Azure, or GCP, including Docker and CI/CD pipeline usage.
LLMOps and AgentOps Best Practices
Review methods for monitoring, evaluating, and optimizing LLM-powered systems for cost, latency, and reliability.
Questions to ask
, 6 itemsWhat are the main challenges your team faces in deploying and maintaining agentic AI systems in production?
Why ask this? To understand the technical and operational pain points and how your experience can address them.
How does the team approach evaluation and monitoring of AI system performance and reliability?
Why ask this? To gauge the maturity of LLMOps/AgentOps practices and where you can contribute.
What frameworks and tools are most commonly used for agent workflow orchestration and retrieval in your stack?
Why ask this? To clarify the technical environment and align your preparation.
How is collaboration structured between AI engineers, data scientists, and backend teams?
Why ask this? To assess cross-functional workflows and communication expectations.
What opportunities exist for contributing to reusable components or technical innovation within the team?
Why ask this? To identify areas for technical leadership and growth.
How does the team balance rapid innovation with the need for production reliability and scalability?
Why ask this? To understand the team's approach to risk and quality management.
Register now to upload your CV
Create a free account, save a PDF or Word CV, and quick apply on roles that take applications here.