[Remote] Generative AI Applications Engineer (Agents & RAG)

Note: The job is a remote job and is open to candidates in USA. Accenture Federal Services is dedicated to helping the US federal government enhance national security and improve people's lives. The Generative AI Applications Engineer will develop secure and scalable GenAI applications, focusing on mission needs and working collaboratively across various teams to ensure successful deployment and operational excellence.ResponsibilitiesDesign & ship mission grade GenAI: Build agentic workflows and RAG systems tailored to mission data and environments; target low hallucination, tight p95 latency, and predictable costAgent frameworks & orchestration: Apply patterns from LangChain/LlamaIndex/Semantic Kernel; design task decomposition, tool use, guardrails, and recovery/fallback strategiesPlatform 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/fallbackRAG 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 noiseProduction rigor: Instrument metrics/logs/traces; run A/B experiments; maintain incident playbooks; and implement safety & compliance guardrailsSRE & FinOps for AI: Define SLIs/SLOs (quality/latency/safety/cost), run on call and postmortems, reduce MTTR; meter usage and optimize token/spendReusable platform components: Ship SDKs, CI/CD templates, Terraform/IaC modules, evaluation harnesses that accelerate multiple mission team not one-off projectsOperate in real world constraints: Deliver into hybrid, restricted, or air gapped environments with Zero Trust principles and audit ready controlsSkillsEnd-to-end ownership of production systems: integration → deployment → observability → incident responseHands-on experience with LLMs, transformer based apps, and RAG in productionStrong PythonExperience with vector search and retrieval (Pinecone, Weaviate, OpenSearch, pgvector, FAISS/Chroma) and grounding AI in enterprise/mission dataU.S. CitizenshipIntegration with leading cloud AI services or on prem inference stacksBackground in LLM evaluation, prompt authoring/testing, A/B experimentation, and LLM OpsResponsible AI expertise (privacy, security, bias, transparency, human in the loop) and data governanceExperience implementing tool using agents for API integration and external data accessContainerization & orchestration (Docker, Kubernetes, VMware) and scripting/automation (Linux Bash, PowerShell)Prior work in regulated/secure environments (e.g., ATO, STIGs, Zero Trust) with fast shippingFamiliarity with NVIDIA AI Foundations, OpenAI ChatGPT, and AI assisted dev tools (Cursor, Windsurf, Claude)Contributions to internal frameworks or opensource; mentorship of engineersClear communication with engineers, PMs, and security/compliance stakeholdersBenefitsCertificationsIndustry trainingHands-on experienceAccenture Federal Services offers a wide variety of benefits. [You can find more information on benefits here.](https://www.accenture.com/us-en/careers/your-future-rewards-benefits)Company OverviewAccenture Federal Services is a leading US federal services company and subsidiary of Accenture. It was founded in 1989, and is headquartered in Arlington, Virginia, USA, with a workforce of 10001+ employees. Its website is https://www.afs.com.