Generative AI Applications Engineer (Agents & RAG)
Core
Build secure, mission-grade Generative AI applications (agentic workflows, RAG) for US federal government programs without model training.
Role type
Generative AI Applications Engineer (Agents & RAG)
Builds
Production GenAI apps for defense, national security, public safety, and military health organizations
Domain
US Federal Government / Generative AI
Deliverable
production ML models
Required skills
Agentic workflow design, RAG pipeline construction, LLM selection & evaluation, Prompt & policy design, Vector search implementation, SRE & FinOps for AI, Platform integration (managed services), Observability & incident management
Preferred skills
Experience with LangChain/LlamaIndex/Semantic Kernel, Knowledge of AWS Bedrock/Azure OpenAI/Google Vertex AI, Familiarity with Pinecone/Weaviate/OpenSearch
Technologies
LangChain, LlamaIndex, Semantic Kernel, AWS Bedrock, Azure OpenAI, Google Vertex AI, Amazon Kendra, Pinecone, Weaviate, OpenSearch, pgvector, FAISS, Chroma
Responsibilities
Design and ship mission-grade GenAI with low hallucination and tight latency; Implement agent frameworks and orchestration patterns; Integrate with managed LLM platforms; Evaluate and select LLMs; Build retrieval pipelines and vector search; Maintain production rigor with metrics and safety guardrails; Define SLIs/SLOs and optimize token spend
Seniority
Mid-to-Senior, hands-on IC