Generative AI Applications Engineer (Agents & RAG)
Accenturefederalservices · Washington, DC
About this role
**Accenture Federal Services — Generative AI Applications Engineer (Agents & RAG)** At Accenture Federal Services (AFS), nothing matters more than helping the US federal government make the nation stronger and safer—and improve life for people. Join a collaborative, inclusive team shipping production GenAI apps for confidential federal programs across defense, national security, public safety, civilian, and military health. > **Confidentiality matters:** Program details aren’t disclosed publicly. If you advance, specifics will be shared during the process. --- ## Role Overview You’ll turn mission needs into secure, reliable, scalable GenAI applications **without requiring model training**. This is a hands-on role spanning **agentic workflows, RAG, prompt/policy design, LLM evaluation, and platform integration**—owning the end-to-end path from **use-case evaluation → production deployment → operational excellence**. --- ## What You’ll Do (Day to Day) - **Design & ship mission-grade GenAI:** Build agentic workflows and RAG systems tailored to mission data and environments, targeting low hallucination, tight p95 latency, and predictable cost. - **Agent frameworks & orchestration:** Use patterns from **LangChain / LlamaIndex / Semantic Kernel** to design task decomposition, tool use, guardrails, and recovery/fallback strategies. - **Platform integration (no model training):** Implement solutions 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, and cost; author/test prompts and policies; deploy with observability and safe rollback/fallback. - **RAG done right:** Build retrieval pipelines and vector search using **Pinecone, Weaviate, OpenSearch, pgvector, FAISS/Chroma**; handle data prep, chunking, metadata, and IR-style evaluations (e.g., **NDCG**) to maximize signal-to-noise. - **Production rigor:** Instrument metrics/logs/traces; run A/B experiments; maintain incident playbooks; implement safety & compliance guardrails. - **SRE & FinOps for AI:** Define **SLIs/SLOs** (quality/latency/safety/cost), support on-call and postmortems, reduce MTTR, and optimize token/spend. - **Reusable platform components:** Ship **SDKs, CI/CD templates, Terraform/IaC modules, and evaluation harnesses** to accelerate multiple mission teams.
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.