Generative AI Platform Engineer

About this role

Accenture Federal Services seeks a Generative AI Platform Engineer to operationalize production LLM/RAG systems for federal government agencies, focusing on reliability, security, and cost optimization. You'll build reusable platform components, implement safety guardrails, and establish observability practices for AI services deployed in regulated environments.

What you'll do

• Stand up and harden LLM/RAG services with enterprise data grounding and low hallucination rates
• Implement guardrails, governance, prompt management, and audit trails aligned to federal compliance requirements
• Define SLIs/SLOs for quality, latency, safety, and cost; instrument metrics and lead incident response
• Optimize performance and reduce costs through caching, batching, autoscaling, and FinOps practices
• Ship reusable SDKs, CI/CD templates, and Infrastructure-as-Code modules for multiple mission teams
• Conduct offline/online evaluations and apply information retrieval metrics to improve system quality

What they're looking for

• Python programming
• Vector search and retrieval systems (pgvector, Milvus, OpenSearch)
• LLM/RAG operationalization and inference stacks
• Site reliability engineering (SLOs, observability, incident response)
• Cloud AI services or on-premises deployment
• FinOps and cost optimization
• Regulated environment compliance (FedRAMP, ATO processes)
• AI safety testing and evaluation frameworks

Benefits

• Glassdoor Top 100 Best Place to Work recognition
• Hands-on experience with cutting-edge generative AI in production
• Professional development through certifications and industry training
• Collaborative, caring community culture
• Fast-paced environment shipping capabilities in weeks not quarters
• Impact on mission-critical federal programs