AI Engineer

What you'll do

• Design, build, and operate production-grade AI systems and multi-agent applications at scale.
• Own the full lifecycle of ML solutions from data pipelines to model development and evaluation.
• Deploy and manage AI applications in cloud-native environments using AWS or Azure services.
• Design and evaluate RAG pipelines while optimizing for latency, caching, and retrieval.
• Implement observability by setting up tracing, metrics, and performance dashboards using tools like OpenTelemetry.
• Develop APIs and services using frameworks such as FastAPI, Flask, or Node.js.
• Deploy models, agents, and applications through automated CI/CD pipelines.
• Utilize AI-assisted coding tools to accelerate the development of complex software tasks.

What we're looking for

• Bachelor's degree in CS, Engineering, or STEM field.
• Ability to obtain a Secret clearance.
• 3+ years of experience building production systems and applications, including AI/ML applications.
• 2+ years of experience developing Generative AI applications using LLMs, RAG frameworks, and vector stores.
• Experience designing and building APIs and services with FastAPI, Flask, or Node.js.
• Experience working in cloud-native environments like AWS and Azure with services like Bedrock, SageMaker, EKS, and S3.
• Experience with agent orchestration frameworks like LangGraph and Strands, and implementing observability via OpenTelemetry or Datadog.
• Experience deploying models, agents, or applications via CI/CD.
• Experience supporting DoW clients or other federal mission environments (preferred).
• Experience with advanced agentic patterns, enterprise data platforms like Databricks, or large data processing pipelines (preferred).
• Master’s degree (preferred).