Senior AI Native Software Engineer (Agentic Systems)

About the role

Accenture is hiring a Senior AI Native Software Engineer in Braga to build production-grade agentic AI systems used in real enterprise environments. The role works directly with client engineering teams, leads technical design sessions and builds reusable patterns and accelerators that scale beyond individual engagements. It is a full-time position.

Key responsibilities

• Architect and govern production-grade agentic systems at enterprise scale: multi-agent orchestration, RAG pipelines, policy-based routing, memory management and programme-level observability.
• Define RAG pipeline standards across engagements, including chunking and embedding strategies and quality benchmarks.
• Set multi-LLM integration standards with vendor-agnostic architecture, fallback routing and cost governance across providers such as OpenAI, Anthropic, Vertex AI and open-source models.
• Own LLMOps at programme scale: eval strategy, prompt governance, observability tooling standards, safety monitoring and cost controls.
• Lead client engineering engagements at senior level, facilitating architecture design and proof-of-concept delivery.
• Shape and publish reusable patterns, accelerators and engineering standards.
• Own the measurement framework for agentic system quality (accuracy, latency, safety, cost) and present AI impact to senior client stakeholders.

Required profile

• Production software engineering experience.
• Hands-on experience designing and deploying agentic AI solutions in production, which is non-negotiable.
• Demonstrated experience with agentic orchestration frameworks such as LangGraph, CrewAI or AutoGen at production depth.
• Experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code.
• Experience owning RAG pipelines: embeddings, chunking strategy, vector databases and context engineering.
• People lead responsibilities: experience managing, developing and performance-managing a team of engineers.

Required skills

• LLMOps fundamentals: eval harness design, prompt versioning and production observability.
• Cloud-native engineering: Kubernetes, Docker, microservices, serverless, CI/CD and IaC (Terraform or Helm).
• Strong Python; Java or an equivalent backend language is acceptable.

The employer states that candidates who have shipped several production agentic systems are preferred over generalists with only passive AI exposure. The advert also mentions vendor fellowship access and a pathway to the Forward Deployed Engineer programme.