Description

You will design and build production-grade AI agents and cloud-native services, owning the full lifecycle from orchestration to observability.

Responsibilities

• Design and implement AI agents using RAG, orchestration workflows, and tool/function invocation.
• Build evaluation frameworks to measure accuracy, latency, and reliability of AI systems.
• Develop scalable microservices and APIs using containers, serverless patterns, and event-driven architectures.
• Implement CI/CD pipelines and Infrastructure as Code (Terraform, Helm) to ensure production readiness.
• Integrate AI providers (OpenAI, Anthropic, Vertex AI) and optimize model usage for cost and performance.

Required Skills

• 10+ years of software engineering experience with strong backend proficiency in Python or Java.
• Hands-on experience building and deploying AI/LLM systems in production, including agents and RAG.
• Deep knowledge of cloud-native development: Docker, Kubernetes, Microservices, and Serverless.
• Experience with AI platforms such as OpenAI, Claude, Vertex AI, or similar providers.
• Proficiency with agent frameworks like LangGraph, AutoGen, or CrewAI.
• Strong background in CI/CD, Infrastructure as Code, and monitoring/observability tools.
• Experience designing multi-agent or distributed AI systems and enterprise-scale integrations.

Preferred Skills

• Experience optimizing AI workloads for cost, latency, and throughput.
• Familiarity with policy-based routing and abstraction layers for multi-model architectures.

Key Skills

Education

Bachelor's degree