Production-Grade AI Agent Engineer (Onsite)

Tech Mirrors; Santa Clara (CA); On-site; USD 140,000 - 210,000; Full time

Job summary

Tech Mirrors in Santa Clara, CA is seeking an AI Engineer to build production-grade agentic AI systems for enterprise use. You will develop multi-agent workflows, integrate LLMs, and support deployment and automation to run reliably and securely in production.

This is a hands-on engineering engagement focusing on agents, orchestration logic, and supporting infrastructure that handles real production workloads, not proof-of-concept or advisory work.

Qualifications

• 3-5 years in Machine Learning, AI or related field with production systems.
• At least 1 year building custom agentic AI applications.
• Strong Python skills and modern development practices.
• Hands-on experience with LLMs and prompt engineering.
• Experience building AI agents with LangGraph.
• Experience with enterprise cloud AI platforms and cloud deployment.
• REST APIs, WebSockets, and event-driven systems knowledge.
• CI/CD tooling (Jenkins) and Git version control.
• Excellent written and verbal communication; independent in cross-functional teams.
• Data layer integration with source systems for agentic apps.

Responsibilities

• Build AI agents and multi-agent systems using LangGraph and LangChain tools.
• Develop and tune prompt engineering workflows across multiple LLMs.
• Develop REST APIs, WebSocket services, and event-driven pipelines for real-time AI services.
• Automate testing and releases through Jenkins CI/CD, and maintain code/docs with Git/Jira/Confluence.
• Deployment of AI applications in enterprise with best practices.
• Coordinate with platform, security, and product teams for scalable deployments.

Skills

Machine Learning

AI Systems

Python

LLMs

Agentic AI

Tools

LangGraph

LangChain

Jenkins

Git

Confluence

Job description

Tech Mirrors in Santa Clara, CA is seeking an AI Engineer to build production-grade agentic AI systems for enterprise use. You will develop multi-agent workflows, integrate LLMs, and support deployment and automation to run reliably and securely in production.

This is a hands-on engineering engagement focusing on agents, orchestration logic, and supporting infrastructure that handles real production workloads, not proof-of-concept or advisory work.