Description

Build and operate complex production systems, AI agent workflows, and Kubernetes infrastructure.

This role is on-site.

Responsibilities

• Develop features using TypeScript, Python, Go, and Java.
• Build and evaluate LLM-powered applications using LangGraph and LangChain.
• Operate Kubernetes controllers, custom resources, and Helm charts with GitOps deployments.
• Implement automated evaluations, load tests, and performance monitoring for AI agents.
• Manage AWS infrastructure on EKS, including networking, storage, and multi-region reliability.

Required Skills

• 8+ years of professional software engineering experience owning complex production systems.
• Strong full-stack experience with production React applications and distributed backend services.
• Proficiency in TypeScript, Python, Go, and Java.
• Hands-on experience with AI coding agents like Claude or Cursor.
• Deep AWS expertise with EKS, EC2, S3, VPC networking, and infrastructure as code (CDK or CloudFormation).
• Applied AI engineering experience with LangGraph, LangChain, or comparable frameworks.
• Production Kubernetes experience including CRDs, custom controllers, and GitOps.
• Strong observability skills: logs, metrics, alarms, incident response, and failure recovery.
• Experience with websockets, streaming systems, and real-time user experiences.

Preferred Skills

• Experience with AI Eval platforms and tools.
• Background in building active-active or active-passive architectures.

Bachelor’s degree or higher in Computer Science or equivalent practical experience.

Key Skills

Education

Any Graduate