Description

You will design, build, and operate AI agent workloads across MCP servers and agents.

This role is remote.

Responsibilities

• Develop agentic AI features, prompt engineering patterns, and LLM integrations for production use.
• Own deployment, scaling, reliability, and cost-efficiency for services running on Kubernetes and Docker in Google Cloud.
• Design and implement Retrieval-Augmented Generation (RAG) pipelines, integrating vector stores and retrieval tooling.
• Implement and maintain core MCP server and agent code, APIs, and SDKs for model orchestration.
• Ensure system observability by implementing logging, metrics, traces, and defining SLOs for model infrastructure.

Required Skills

• 5+ years of strong software engineering experience in Python or Node.js.
• 5+ years of experience with Kubernetes, Docker, CI/CD, and infrastructure-as-code.
• 2+ years of experience working with LLMs, prompt engineering, and agent frameworks.
• 2+ years of practical experience implementing RAG, including embeddings, vector DBs, and retrieval tuning.
• 2+ years of experience using LangChain patterns and tracing tools like Langfuse for model traceability.
• 2+ years of practical experience with Google Cloud Platform services.
• 2+ years of experience with observability, testing, and security practices for distributed systems.
• 2+ years of experience evaluating and mitigating hallucinations and leakage risks in RAG systems.
• Familiarity with CI/CD pipelines such as Jenkins or GitHub Actions.

Key Skills

Education

Any Gradute