AI Native SW Engineer
On-siteDublin, Leinster, Ireland
Job Summary
Design and deploy production-grade agentic AI systems end-to-end, including multi-agent orchestration, RAG pipelines, and policy-based routing. Build and own RAG pipelines with embeddings, chunking strategies, and vector search tuned against real quality targets. Integrate multiple LLM providers with fallback routing and manage token, cost, and latency tradeoffs. Implement LLMOps with eval harnesses, prompt versioning, and observability using tools like LangSmith. Embed with client engineering teams to design proofs of concept and build reusable accelerators that scale beyond individual engagements. Define metrics for agent accuracy, latency, and safety; present findings to stakeholders in business terms. Requires minimum one year of hands-on experience with agentic frameworks at production depth and cloud-native engineering maturity.
Required Qualifications
- Minimum 1 year of hands-on experience designing and deploying agentic AI solutions in a production environment
- Demonstrated experience with agentic orchestration frameworks: LangGraph, CrewAI, AutoGen, or equivalent
- Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code
- RAG pipeline ownership: embeddings, chunking strategy, vector databases, and context engineering
- LLMOps fundamentals: eval harness design, prompt versioning, and production observability
- Cloud-native engineering maturity: Kubernetes, Docker, microservices, serverless, CI/CD, and IaC (Terraform or Helm)
- Strong Python
- Java or equivalent backend language acceptable
- Production debugging and observability experience
Desired Qualifications
- Quality of experience is weighted over years, a candidate who has shipped three production agentic systems in four years is preferred over a generalist with passive AI exposure
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.