AI Engineer

What you'll do

• Design and deliver production-grade AI systems and RAG pipelines for mission-critical federal environments.
• Build embedding pipelines including document ingestion, chunking strategies, indexing, and hybrid search.
• Develop and manage APIs and services using frameworks like FastAPI, Flask, or Node.js.
• Implement observability by tracking latency, throughput, token usage, and error rates using OpenTelemetry or Datadog.
• Optimize performance using caching layers, parallelization, and automated evaluation pipelines with LLM-as-a-judge techniques.
• Support production AI services through deployment, monitoring, incident response, and performance tuning.
• Manage prompt templates, versioning, model configurations, and structured outputs across development and production environments.
• Implement AI security measures including prompt injection resistance, data leakage prevention, and guardrails.

What we're looking for

• Ability to obtain a TS/SCI clearance.
• 3+ years of experience building production systems, including AI/ML applications.
• Experience building LLM systems using RAG frameworks, custom pipelines, and vector stores like Pinecone, Weaviate, FAISS, or OpenSearch.
• Experience designing embedding pipelines, chunking strategies, and APIs using FastAPI, Flask, or Node.js.
• Experience with cloud-native architectures including AWS services (Bedrock, SageMaker, EKS, S3, Lambda) and agent frameworks like LangGraph.
• Experience implementing observability with OpenTelemetry or Datadog and optimizing performance using Redis or parallelization.
• Experience supporting production AI services, including deployment, monitoring, and knowledge of AI security concepts like prompt injection.
• Bachelor's degree.