CareerPlanGet AI match score →

Generative AI Applications Engineer (Agents & RAG)

Seattle, WA💼 Full-time🗓 2026-05-18 → 2026-07-31

Core

Build secure, mission-grade Generative AI applications (agents and RAG) for US federal government programs across defense, national security, and public safety.

Role type

Generative AI Applications Engineer (Agents & RAG)

Builds

Production GenAI apps, agentic workflows, RAG systems, and reusable platform components for federal clients.

Domain

US Federal Government (Defense, National Security, Public Safety)

Deliverable

production ML models

Required skills

Agentic workflow design, RAG system architecture, LLM selection and evaluation, Prompt and policy design, Vector search implementation, Cloud platform integration (AWS/Azure/GCP), Observability and SRE practices, FinOps for AI, Terraform/IaC, CI/CD pipeline creation

Preferred skills

Experience with LangChain/LlamaIndex/Semantic Kernel, Knowledge of NDCG and retrieval metrics, Experience with Document AI services

Technologies

AWS Bedrock, Azure OpenAI, Google Vertex AI, Amazon Kendra, Pinecone, Weaviate, OpenSearch, pgvector, FAISS, Chroma, Terraform

Responsibilities

Design and ship mission-grade GenAI with low hallucination and tight latency; Implement agent frameworks and orchestration patterns; Integrate with managed cloud AI services; Evaluate and select LLMs for quality and safety; Build retrieval pipelines and vector search systems; Maintain production rigor with metrics, logs, and safety guardrails; Define SLIs/SLOs and optimize token spend; Ship reusable SDKs and infrastructure modules.

Seniority

Mid-to-Senior, hands-on IC

Rewrite
## Responsibilities - Design & ship mission grade GenAI: Build agentic workflows and RAG systems tailored to mission data and environments; target low hallucination, tight p95 latency, and predictable cost. - Agent frameworks & orchestration: Apply patterns from LangChain/LlamaIndex/Semantic Kernel; design task decomposition, tool use, guardrails, and recovery/fallback strategies. - Platform integration (no model training): Implement with AWS Bedrock, Azure OpenAI, Google Vertex AI, Amazon Kendra, and managed services (e.g., Document AI, Gemini, Gemma). - LLM selection & evaluation: Compare models for quality, safety, latency, cost; author/test prompts & policies; deploy with observability and safe rollback/fallback. - RAG done right: Build retrieval pipelines & vector search (Pinecone, Weaviate, OpenSearch, pgvector, FAISS/Chroma); handle data prep, chunking, metadata, and IRstyle evals (e.g., NDCG) to maximize signal to noise. ## Requirements - You’ll turn mission needs into secure, reliable, and scalable GenAI applications no model training required. - This is a hands-on role across agentic workflows, RAG, prompt/policy design, LLM evaluation, and platform integration. - You’ll own the end-to-end path from use case evaluation → production deployment → operational excellence, partnering with product, security, data, and SRE to ship features safely and at scale. ## Nice to Have - N/A ## Benefits - Join Accenture Federal Services, a technology company within global Accenture. Recognized as a Glassdoor Top 100 Best Place to Work, we offer a collaborative and caring community where you feel like you belong and are empowered to grow, learn and thrive through hands-on experience, certifications, industry training and more. - We ship in weeks, not quarters, and measure success with latency, reliability, safety, and cost. - Confidentiality matters: We don’t disclose program details publicly. If you advance, we’ll share specifics during the process. - Join us to drive positive, lasting change that moves missions and the government forward!
Sourced via greenhouse · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.
Apply on Greenhouse ↗