AI Engineer
TechJobs.ie Job Insights
At a glance
Technologies & skills
What you'll be doing
Join a Dublin-based AI team shipping LLM features from idea to production. You'll own AI features end-to-end: scoping, building, evaluating, and optimizing for latency and cost. Work involves RAG and agent-based workflows, model evaluation, and deploying on cloud platforms with containers.
- Own AI features from scoping to production
- Build RAG and agent-based workflows on commercial and open-source models
- Set up evaluation to measure feature impact
- Optimize latency and cost while maintaining answer quality
Key requirements
Must-have
- Solid software engineering background in Python
- Experience shipping ML or LLM features to production
- Hands-on experience with embeddings, vector search, and model evaluation
- Comfort working on AWS, Azure, or GCP with containers
- Sound judgement about AI applicability
Nice-to-have
- Fine-tuning experience
- MLOps experience
Role signals
- Technical focus
- AI feature development, production ML/LLM workflows
- Architecture / system design
- Indicated in the listing
- Hands-on vs management
- Hands-on
Similar jobs
Full job description
AI Engineer | Dublin, hybrid
Plenty of companies say they're "doing AI". This one ships it. Our client's AI team takes LLM features from idea to production, and real customers use them every day. They're hiring an engineer to help them move faster.
The work
You'll own AI features from start to finish. That means scoping the problem, choosing the right approach, building it, and making sure it holds up in production. Day-to-day, you can expect:
-
Building RAG and agent-based workflows on top of commercial and open-source models
-
Setting up evaluation so you know when a change makes things better or worse
-
Bringing down latency and cost without losing answer quality
You'll likely have
-
A solid software engineering background in Python, with time spent shipping ML or LLM features to production
-
Hands-on experience with embeddings, vector search and prompt or model evaluation
-
Comfort working on a cloud platform (AWS, Azure or GCP) with containers
-
Sound judgement about when AI is the right tool
Fine-tuning or MLOps experience is a bonus, but it's not essential.
Interested? Apply below or contact Ashton Simms at Reperio Human Capital for a confidential chat about the role.
Reperio Human Capital acts as an Employment Agency and an Employment Business.
Interview prep pack
Grounded in this listing. Use it to prepare examples before you apply.
Your interview focus
Based on this listing, the AI Engineer role focuses on end-to-end development and deployment of AI features, particularly leveraging LLMs, embeddings, and cloud platforms. The position emphasizes hands-on engineering, production readiness, and optimization of AI workflows.
- Hands-on AI feature development·High
- Production ML/LLM workflow experience·High
- Cloud and container deployment·Medium
- Optimization (latency/cost)·Medium
Only have 30 minutes?
Follow a focused preparation plan based on this job.
Start 30-minute prep
Your 30-minute plan
Review Recent Projects Involving LLMs and Production ML
0–8 minSelect 1-2 projects where you owned the end-to-end delivery of AI features, focusing on your technical and decision-making contributions.
Refresh Knowledge of RAG, Embeddings, and Vector Search
8–15 minStudy the latest developments and best practices in RAG workflows, embeddings, and vector databases relevant to the role.
Summarize Cloud and Containerization Experience
15–20 minPrepare concise examples of deploying AI solutions on AWS, Azure, or GCP using containers, highlighting automation and scaling.
Prepare for Evaluation and Optimization Discussions
20–25 minList concrete methods you've used to evaluate, monitor, and optimize AI systems for latency, cost, and quality.
Draft Role-Specific Questions
25–30 minWrite down 3-4 thoughtful questions about the team's workflows, challenges, and technical stack to ask during the interview.
Talking points
, 5 itemsEnd-to-End AI Feature Ownership
Be ready to discuss examples where you scoped, built, and deployed AI features, highlighting your ability to manage the full lifecycle.
RAG and Agent-Based Workflow Implementation
Prepare to explain your experience building Retrieval-Augmented Generation (RAG) or agent-based systems, including model selection and integration.
Evaluation and Monitoring of AI Systems
Show how you set up evaluation frameworks to measure the impact of changes and ensure answer quality in production.
Optimizing for Latency and Cost
Demonstrate your approach to reducing latency and cost in AI systems without sacrificing performance or quality.
Cloud Platform and Containerization Experience
Be ready to detail your hands-on experience deploying AI solutions on AWS, Azure, or GCP using containers.
What to research
, 4 itemsReview RAG and Agent-Based Workflow Patterns
Refresh your understanding of Retrieval-Augmented Generation and agent-based architectures, including recent tools and best practices.
Brush Up on Embeddings and Vector Search
Prepare to discuss your hands-on experience with embeddings, vector databases, and related evaluation techniques.
Revisit Cloud Deployment with Containers
Ensure you can clearly explain your experience deploying AI features on AWS, Azure, or GCP using containers.
Prepare Examples of AI Feature Lifecycle Management
Identify projects where you owned AI features from scoping to production, focusing on challenges and outcomes.
Questions to ask
, 6 itemsWhat types of LLM features are currently in production, and what are the main challenges faced?
Why ask this? To understand the maturity of the AI stack and where your expertise can add value.
How does the team approach evaluation and monitoring of AI features post-deployment?
Why ask this? To gauge the emphasis on quality and reliability in production.
What is the typical workflow for taking an AI feature from idea to production here?
Why ask this? To clarify expectations around ownership and collaboration.
Which cloud platforms and tools are most commonly used for deployment?
Why ask this? To align your experience with their technical environment.
How does the team balance innovation with the need to optimize for latency and cost?
Why ask this? To understand priorities and constraints in the role.
Are there opportunities to contribute to architectural decisions or tool selection?
Why ask this? To assess your potential influence on technical direction.
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.