Generative AI Applications Engineer (Agents & RAG)

Accenture Federal Services•Fairfield, CA

17h•$103,200 - $203,400•Hybrid

About The Position

At Accenture Federal Services (AFS), we are dedicated to strengthening the US federal government and improving the lives of its citizens through technology and innovation. Our team of over 13,000 professionals works across defense, national security, public safety, civilian, and military health organizations. AFS, a technology company within the global Accenture network, is recognized as a Glassdoor Top 100 Best Place to Work. We foster a collaborative and inclusive community that empowers individuals to grow, learn, and thrive through hands-on experience, certifications, and industry training. We are seeking individuals to join us in driving positive, lasting change that advances critical missions and the government forward. We specialize in building production-ready Generative AI applications for confidential federal programs, prioritizing reliability, privacy, and safety. Our approach focuses on rapid development cycles, shipping in weeks rather than quarters, and measuring success by latency, reliability, safety, and cost. Confidentiality is paramount, and program details are not publicly disclosed. Specifics will be shared during the interview process for qualified candidates.

Requirements

Built and deployed a production GenAI application (chatbot, copilot, assistant, or enterprise AI).
Hands-on experience with LLMs such as GPT, Claude, Llama, Gemini, Mistral, via APIs or self-hosted.
Designed and implemented RAG solutions using embeddings, vector databases, and semantic search for enterprise or mission data.
Shipped AI applications with frameworks like LangChain, LangGraph, LlamaIndex, Semantic Kernel, DSPy, or similar.
Strong Python development skills for building and integrating AI/ML applications.
Experience owning AI solutions through the full production lifecycle, including deployment and operational support.
Active U.S. citizenship.

Nice To Haves

Integration with leading cloud AI services or on-prem inference stacks.
Background in LLM evaluation, prompt authoring/testing, A/B experimentation, and LLM Ops.
Responsible AI expertise (privacy, security, bias, transparency, human in the loop) and data governance.
Experience implementing tools using agents for API integration and external data access.
Familiarity with containerization & orchestration (Docker, Kubernetes, VMware) and scripting/automation (Linux Bash, PowerShell).
Prior work in regulated/secure environments (e.g., ATO, STIGs, Zero Trust) with fast shipping.
Familiarity with NVIDIA AI Foundations, OpenAI ChatGPT, and AI-assisted development tools (Cursor, Windsurf, Claude).
Contributions to internal frameworks or open source projects; mentorship of engineers.
Clear communication with engineers, PMs, and security/compliance stakeholders.

Responsibilities

Design and ship mission-grade GenAI applications, including agentic workflows and RAG systems, tailored to specific mission data and environments, targeting low hallucination, tight p95 latency, and predictable cost.
Apply agent frameworks and orchestration patterns (e.g., LangChain, LlamaIndex, Semantic Kernel) to design task decomposition, tool use, guardrails, and recovery/fallback strategies.
Integrate with cloud AI platforms such as AWS Bedrock, Azure OpenAI, Google Vertex AI, and managed services like Amazon Kendra, Document AI, Gemini, and Gemma, without requiring model training.
Compare and select LLMs based on quality, safety, latency, and cost; author and test prompts and policies; and deploy applications with observability and safe rollback/fallback mechanisms.
Build robust RAG solutions, including retrieval pipelines and vector search (e.g., Pinecone, Weaviate, OpenSearch, pgvector, FAISS/Chroma), managing data preparation, chunking, metadata, and information retrieval evaluations (e.g., NDCG) to optimize signal-to-noise ratio.
Implement production rigor by instrumenting metrics, logs, and traces; running A/B experiments; maintaining incident playbooks; and implementing safety and compliance guardrails.
Apply SRE and FinOps principles to AI, defining SLIs/SLOs for quality, latency, safety, and cost; participating in on-call rotations and postmortems to reduce MTTR; and metering usage to optimize token and spend.
Develop reusable platform components such as SDKs, CI/CD templates, Terraform/IaC modules, and evaluation harnesses to accelerate multiple mission teams.
Deliver solutions within hybrid, restricted, or air-gapped environments, adhering to Zero Trust principles and audit-ready controls.