Site Reliability Engineer

We are hiring a Senior Agent Platform Engineer to build an enterprise-grade platform on AWS that will support hundreds of production AI agents.

This is not a traditional ML model-development role. The focus is on building the shared platform services required to run agentic applications reliably, securely and at scale.

Responsibilities:

• Design and build Python-based platform services and APIs.
• Implement agent runtime, workflow, session and tool-execution capabilities.
• Integrate Amazon Bedrock, Bedrock AgentCore and enterprise systems.
• Build secure MCP servers and tool gateways.
• Develop evaluation, tracing, monitoring and cost-control capabilities.
• Create deployment patterns using Terraform, containers and AWS managed services.
• Improve reliability, scalability, security and developer experience for agent teams.

Requirements:

• 6+ years in backend, ML platform, MLOps or distributed-systems engineering.
• Strong Python, FastAPI, async programming and API design.
• Experience building agentic systems, LLM applications, RAG or tool-calling workflows.
• Strong AWS experience, including Bedrock, Lambda, ECS/EKS, API Gateway, S3 DynamoDB, OpenSearch, IAM and CloudWatch.
• Experience with Docker, CI/CD and infrastructure as code.
• Good understanding of event-driven systems, orchestration, retries and state management.

Good to Have:

• MLOps and model-serving experience.
• Exposure to Terraform.
• MCP and Bedrock AgentCore.
• Step Functions, Temporal or similar workflow engines.
• Kubernetes and platform engineering.
• OpenTelemetry, evaluation frameworks and LLM observability.
• Knowledge graphs, vector databases and enterprise data platforms.