Description

Design, build, and deploy production-grade AI-driven systems, including agent-based workflows and scalable cloud-native solutions.

This role is hybrid.

Responsibilities

• Design and implement AI agents featuring RAG, orchestration workflows, tool invocation, and policy-based routing.
• Build evaluation frameworks to measure accuracy, latency, and reliability, and implement observability for the agent lifecycle.
• Integrate with AI providers (OpenAI, Anthropic, Vertex AI) and build abstraction layers for multi-model architectures.
• Develop scalable microservices using Docker, Kubernetes, and serverless patterns, supported by CI/CD pipelines and Terraform.
• Define test strategies, debug production systems, and optimize for performance, throughput, and cost.

Required Skills

• 8+ years of software engineering experience.
• Proficiency in Python, Java, or similar backend languages.
• Hands-on experience building and deploying AI/LLM systems in production (agents, RAG, orchestration).
• Strong background in cloud-native systems: APIs, microservices, containers, and serverless.
• Experience with CI/CD pipelines, Infrastructure as Code, and monitoring/observability tools.
• Experience integrating with major AI platforms (OpenAI, Claude, Vertex AI).

Preferred Skills

• Experience with agent frameworks such as LangGraph, AutoGen, or CrewAI.
• Experience designing multi-agent or distributed AI systems.

Key Skills

Education

Any Graduate