Generative AI Applications Engineer – Agents, RAG

🕒 April 1

🏄 California – Remote

🏄 California – Remote

💵 $103.2k - $203.4k / year

⏰ Full Time

🟡 Mid-level

🟠 Senior

💻 Application Engineer

👻 Ghost score 45%

What it means: how likely this posting is sitting open without active hiring.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.How we score it: age, reposts, open roles vs team size, how fast jobs close, and whether pay is listed.Fine print: an estimate from public data, not a judgment of the company. Real jobs can score high, so treat it as a hint, not a fact.

Apply Now

Find Similar Remote Jobs

Set Up Email Alert For New Jobs

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume

Accenture Federal Services

WebsiteLinkedInAll Job Openings

10,000+ employees

Founded 2017

💼 Consulting

🎖️ Defense

📦 Logistics

Consulting • Defense • Logistics

Accenture Federal Services is a division of Accenture that focuses on delivering technology and consulting services to the U. S. federal government. With capabilities in cloud, cybersecurity, data and artificial intelligence, digital engineering, and emerging technologies, Accenture Federal Services supports federal agencies in achieving mission-critical outcomes through innovation and technological advancement. The company emphasizes building secure, scalable solutions, enhancing decision-making with data-driven insights, and transforming digital infrastructures to meet complex governmental needs. By leveraging advanced R&D and human-centered design, they aim to improve the performance and resilience of government operations.

📋 Description

• Build secure, reliable, and scalable generative AI applications for federal missions • Design and ship agentic workflows and RAG systems tailored to mission data and environments • Apply LangChain, LlamaIndex, and Semantic Kernel patterns for task decomposition, tool use, guardrails, and fallback strategies • Integrate AWS Bedrock, Azure OpenAI, Google Vertex AI, Amazon Kendra, Document AI, Gemini, Gemma, and other managed services • Compare and evaluate LLMs for quality, safety, latency, and cost • Author and test prompts and policies; deploy with observability and safe rollback/fallback • Build retrieval pipelines and vector search using technologies such as Pinecone, Weaviate, OpenSearch, pgvector, FAISS, and Chroma • Instrument metrics, logs, and traces; run A/B experiments; maintain incident playbooks; implement safety and compliance guardrails • Define AI SLIs/SLOs, participate in on-call and postmortems, reduce MTTR, and optimize token spending • Ship reusable SDKs, CI/CD templates, Terraform/IaC modules, and evaluation harnesses • Deliver solutions into hybrid, restricted, or air-gapped environments using Zero Trust principles and audit-ready controls • Own the path from use-case evaluation through production deployment and operational excellence while partnering with product, security, data, and SRE teams

🎯 Requirements

• Built and deployed a production GenAI application • Hands-on experience with LLMs including GPT, Claude, Llama, Gemini, and Mistral via APIs or self-hosted • Designed and implemented RAG solutions using embeddings, vector databases, and semantic search • Experience with LangChain, LangGraph, LlamaIndex, Semantic Kernel, DSPy, or similar frameworks • Strong Python development for AI/ML applications • Owned AI solutions through the full production life cycle, deployment, and operational support • Active U.S. citizenship • Integration with leading cloud AI services or on-prem inference stacks (nice to have) • Background in LLM evaluation, prompt authoring/testing, A/B experimentation, and LLM Ops (nice to have) • Responsible AI expertise and data governance (nice to have) • Experience implementing agent tools for API integration and external data access (nice to have) • Containerization and orchestration with Docker, Kubernetes, or VMware; Linux Bash and PowerShell scripting (nice to have) • Prior work in regulated/secure environments such as ATO, STIGs, and Zero Trust (nice to have) • Familiarity with NVIDIA AI Foundations, OpenAI ChatGPT, and AI-assisted development tools including Cursor, Windsurf, and Claude (nice to have) • Contributions to internal frameworks or open source and mentorship of engineers (nice to have) • Clear communication with engineers, PMs, and security/compliance stakeholders (nice to have) • U.S. work authorization without current or future visa sponsorship required

🏖️ Benefits

• Collaborative and caring community • Hands-on growth opportunities • Certifications • Industry training • Wide variety of benefits (specific benefits not listed)