Senior Agentic AI Engineer - LLM & AI Infra Lead

Zenotis Infotech; Burlingame (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Zenotis Infotech is seeking an experienced Agentic AI Engineer to design, build, and operate production-ready AI systems, LLM infrastructure, and autonomous agents. You will collaborate with AI and engineering teams to scale high-performance platforms.

The role emphasizes backend software strength, hands-on AI development, and deploying robust, observable solutions using LangChain, LangGraph, CrewAI, and modern MLOps tooling. Join a fast-growing team in California.

Qualifications

• 7–10 years of software, backend, ML, or infrastructure engineering experience.
• Strong background in Software/Backend Engineering.
• Experience with LLMs / Generative AI / Agentic AI.

Responsibilities

• Build and deploy LLM and Generative AI applications in production.
• Develop and scale AI agents and multi-agent workflows.
• Work with frameworks such as LangChain, LangGraph, and CrewAI.
• Build and optimize LLM serving and inference using tools such as vLLM, Triton, or Ray Serve.
• Manage AI workloads using Kubernetes, Docker, and cloud platforms.
• Build RAG pipelines, memory systems, and integrations with vector databases.
• Implement monitoring, logging, tracing, and evaluation for AI/LLM applications.
• Develop CI/CD pipelines and internal tools for deploying AI models and agents.
• Troubleshoot performance, scalability, GPU, and production issues.

Skills

Backend engineering

Generative AI / Agentic AI

LangChain / LangGraph / CrewAI

Kubernetes

Docker

Cloud platforms (AWS/GCP/Azure)

Tools

vLLM

Triton

Ray Serve

Kubernetes

Docker

Job description

Zenotis Infotech is seeking an experienced Agentic AI Engineer to design, build, and operate production-ready AI systems, LLM infrastructure, and autonomous agents. You will collaborate with AI and engineering teams to scale high-performance platforms.

The role emphasizes backend software strength, hands-on AI development, and deploying robust, observable solutions using LangChain, LangGraph, CrewAI, and modern MLOps tooling. Join a fast-growing team in California.