Tech Stack

Description

You'll turn mission needs into secure, reliable, and scalable GenAI applications, focusing on agentic workflows, RAG, prompt/policy design, LLM evaluation, and platform integration. You'll own the end-to-end path from use case evaluation to production deployment and operational excellence, partnering with product, security, data, and SRE teams to ship features safely and at scale. This role involves building AI applications for confidential federal programs where reliability, privacy, and safety are critical.

Requirements

• End-to-end ownership of production systems from integration to incident response
• Hands-on experience with LLMs, transformer-based apps, and RAG in production
• Strong Python skills
• Experience with vector search and retrieval technologies like Pinecone, Weaviate, OpenSearch, pgvector, FAISS/Chroma
• U.S. Citizenship

Responsibilities

• Design and ship mission-grade GenAI applications with agentic workflows and RAG systems
• Apply agent frameworks orchestration using patterns from LangChain/LlamaIndex/Semantic Kernel
• Implement platform integration with AWS Bedrock, Azure OpenAI, Google Vertex AI, and other managed services
• Conduct LLM selection and evaluation for quality, safety, latency, and cost
• Build retrieval pipelines with vector search technologies like Pinecone, Weaviate, and OpenSearch
• Instrument metrics, logs, and traces for production rigor and run A/B experiments
• Define SLIs/SLOs for quality, latency, safety, and cost, and optimize token/spend
• Ship reusable platform components such as SDKs, CI/CD templates, and Terraform/IaC modules
• Operate in hybrid, restricted, or air-gapped environments with Zero Trust principles