AI Engineer

GCS Recruitment; United States; Remote; USD 84,000 - 124,000; Full time

Job summary

Big Tech in Dublin is hiring an AI Engineer to scale production AI systems, focusing on LLM-powered applications and RAG-enabled pipelines. You will work in a core AI product engineering team embedded in Dublin, delivering shipped features and robust inference across large GPU fleets.

The role requires hands-on experience with LLMs in production, Python and ML infra familiarity, and comfort with evolving tooling in a fast-moving environment.

Qualifications

• Hands-on production LLM experience.
• Strong Python and ML infra skills.
• Familiar with vector databases and RAG.

Responsibilities

• Designing and deploying LLM-powered applications in production.
• RAG architecture - retrieval pipelines, vector search, embedding strategy, chunking and re-ranking for relevance at scale
• Inference optimisation - quantisation, batching, and latency/throughput tradeoffs across large GPU fleets
• Agentic systems - tool use, multi-step reasoning, orchestration frameworks for autonomous task execution
• Fine-tuning and evaluation pipelines for foundation models, including guardrails and eval harnesses for production reliability
• Cross-functional work with research, infra, and product teams - translating frontier techniques into shipped features

Skills

Python

PyTorch

LLMs in production

Prompt engineering

Vector databases

Tools

Llama

Mistral

Pinecone

Weaviate

pgvector

Job description

AI Engineer - LLMs, RAG & Inference Systems

Big Tech, Dublin - Full-Time

One of the world's leading technology companies is scaling its AI engineering function in Dublin - building production AI systems at the frontier, not research that never ships. This is a full-time seat on a team shipping LLM-powered products used at genuine scale.

What you'll work on:

• Designing and deploying LLM-powered applications in production, not prototypes
• RAG architecture - retrieval pipelines, vector search, embedding strategy, chunking and re-ranking for relevance at scale
• Inference optimisation - quantisation, batching, and latency/throughput tradeoffs across large GPU fleets
• Agentic systems - tool use, multi-step reasoning, orchestration frameworks for autonomous task execution
• Fine-tuning and evaluation pipelines for foundation models, including guardrails and eval harnesses for production reliability
• Cross-functional work with research, infra, and product teams - translating frontier techniques into shipped features

What we're looking for:

• ~2 years' experience, with genuine hands-on exposure to LLMs in production (not just personal projects)
• Strong Python, comfortable with PyTorch or equivalent production ML infra
• Practical experience with LLM APIs (OpenAI, Anthropic, or open-source stacks - Llama, Mistral) and prompt/context engineering
• Understanding of vector databases (Pinecone, Weaviate, pgvector) and RAG design tradeoffs
• Bonus: inference infra experience (vLLM, TensorRT, Triton) or open-source AI tooling contributions
• Comfortable in a fast-moving, ambiguous environment where the tooling changes every few months

Team & setup:

• Embedded within a core AI product engineering team, Dublin office
• Full-time, permanent - Big Tech-scale package with equity component
• Genuine growth path into senior/staff AI engineering as the Dublin function scales