Production GenAI Engineer — Secure, Scalable

Accenture Federal Services; Seattle (WA); Hybrid; USD 122,000 - 203,000; Full time

Job summary

Accenture Federal Services is building mission-grade GenAI applications that are secure, reliable, and scalable for federal programs. You will own end-to-end delivery from use-case evaluation to production deployment, collaborating with product, security, data, and SRE teams.

The role emphasizes agentic workflows, RAG pipelines, platform integration across AWS Bedrock, Azure OpenAI, Vertex AI, and deployment with observability, safety, and cost controls.

Qualifications

• Hands-on production GenAI experience and deployment
• Strong Python development for AI/ML integrations
• Familiarity with LLMs and evaluation techniques
• Experience building RAG and vector search solutions

Responsibilities

• Design & ship mission-grade GenAI applications with low latency
• Implement agentic workflows and RAG pipelines for secure environments
• Integrate platforms (AWS Bedrock, Azure OpenAI, Vertex AI) without model training
• Evaluate models for quality, safety, latency, and cost; implement guardrails and rollback

Skills

GenAI

Python

LLM evaluation

RAG systems

Tools

LangChain

LlamaIndex

Semantic Kernel

Job description

Accenture Federal Services is building mission-grade GenAI applications that are secure, reliable, and scalable for federal programs. You will own end-to-end delivery from use-case evaluation to production deployment, collaborating with product, security, data, and SRE teams.

The role emphasizes agentic workflows, RAG pipelines, platform integration across AWS Bedrock, Azure OpenAI, Vertex AI, and deployment with observability, safety, and cost controls.