Generative AI Applications Engineer (Agents & RAG)
Core
Build secure, mission-grade Generative AI applications (agentic workflows, RAG, LLM evaluation) for US federal government programs without model training.
Role type
Senior IC Generative AI Applications Engineer (Agents & RAG)
Builds
Production GenAI apps, SDKs, CI/CD templates, and reusable platform components for defense, national security, and public safety.
Domain
US Federal Government / Generative AI / Cloud AI Services
Deliverable
production ML models
Required skills
Python, LLM APIs (GPT, Claude, Llama, Gemini, Mistral), RAG pipelines, Vector databases (Pinecone, Weaviate, OpenSearch, pgvector, FAISS, Chroma), Agent frameworks (LangChain, LlamaIndex, Semantic Kernel, LangGraph, DSPy), Cloud AI platforms (AWS Bedrock, Azure OpenAI, Google Vertex AI, Amazon Kendra), SRE/FinOps for AI, Terraform/IaC, Docker, Kubernetes, Linux Bash, PowerShell.
Preferred skills
LLM evaluation, Prompt engineering, Responsible AI, Container orchestration, NVIDIA AI Foundations, AI-assisted dev tools.
Technologies
LangChain, LlamaIndex, Semantic Kernel, LangGraph, DSPy, AWS Bedrock, Azure OpenAI, Google Vertex AI, Amazon Kendra, Pinecone, Weaviate, OpenSearch, pgvector, FAISS, Chroma, Terraform, Docker, Kubernetes, Linux, PowerShell, NVIDIA AI Foundations, Cursor, Windsurf, Claude.
Responsibilities
Design and ship agentic workflows and RAG systems; Implement platform integration with managed cloud AI services; Select and evaluate LLMs for quality, safety, and cost; Build retrieval pipelines and vector search; Instrument metrics, run A/B experiments, and maintain incident playbooks; Define SLIs/SLOs and optimize token spend; Ship reusable SDKs and IaC modules; Operate in hybrid, restricted, or air-gapped environments with Zero Trust principles.
Seniority
Senior, hands-on IC
