Z

Senior Agentic AI Infrastructure Engineer

zenotis infotech • United State
Visa Sponsorship
Apply Now
AI Summary

Design and scale high-performance AI infrastructure for LLMs and autonomous agents, bridging research and production. Optimize GPU/TPU clusters, agent orchestration, and observability stacks while building developer platforms for AI deployment. Requires deep expertise in distributed systems, Kubernetes, and LLM serving frameworks.

Key Highlights
Build and maintain scalable AI infrastructure for LLMs, multimodal models, and agentic systems
Optimize GPU/TPU clusters, inference latency, and cost efficiency using modern serving frameworks
Develop observability, evaluation, and reliability pipelines for production AI systems
Key Responsibilities
Design, build, and manage scalable infrastructure for training, fine-tuning, and serving LLMs and multimodal models
Optimize GPU/TPU clusters for high utilization and efficient resource allocation in production environments
Architect and deploy agent orchestration frameworks (e.g., LangGraph, CrewAI) for autonomous AI agents
Implement observability stacks (tracing, prompt logging, cost tracking) for LLMs and agents using tools like Langfuse or Datadog
Build robust state management and memory systems (vector/graph databases) for agentic workflows
Develop internal developer platforms and CI/CD pipelines for AI model and agent deployment
Diagnose and resolve production issues related to memory limits, inference queues, and cluster failures

Searching for Devops roles that provide visa sponsorship? Connect with international employers through Devops Jobs with Visa Sponsorship opportunities actively seeking talented professionals.

Technical Skills Required
Kubernetes Python Distributed Systems
Benefits & Perks
H1-B visa sponsorship

Explore our comprehensive directory of visa sponsorship jobs from employers worldwide who are ready to sponsor talented international professionals.

Nice to Have
Experience with vector databases (Pinecone, Milvus, Qdrant) and RAG pipelines
Understanding of model optimization techniques (quantization, LoRA, KV caching)
Previous experience building platforms in high-growth environments

Job Description

Role: Agentic AI Engineer

Location: Burlingame, CA (Hybrid, 3 days in a week Onsite)

Type: Full-time

Experience range: 7 to 13 years

NOTE: Client will take H1-T as well.

About the Role

We are seeking an experienced Agentic AI Engineer to build, scale, and maintain the critical infrastructure that powers our AI models and autonomous agents. In this role, you will act as the bridge between our AI research/development teams and our production environments. You will not just be deploying models; you will be designing the high-performance, distributed systems required to serve Large Language Models (LLMs), orchestrate multi-agent workflows, and optimize GPU compute at scale.

Want the full job description? Read the complete details on LinkedIn, the original posting.
Continue on LinkedIn

This is a short excerpt. All rights to the full description belong to its original publisher.

Ready to apply?

Apply Now
See Jaabz jobs first on Google 1 tap · free · in AI Overviews Jaabz is on your Google Manage Preferred Sources
Job Overview
Posted Oct 27, 2026
Employment Full-time
Experience Mid-Senior level
Location United State
Category Devops
Company zenotis infotech
Keep exploring

Similar Jobs

Explore other opportunities that match your interests

Hidden company

Log in to see location

Premium

Lead Managed Services Engineer II (Cyber Security & Cloud Infrastructure)

Devops Full-time 10h ago

Log in free to see the details

Hidden company

Log in to see location

Premium

Lead Cloud HPC & AI Infrastructure Architect (Silicon2Service)

Devops Full-time 1d ago

Log in free to see the details

Visas, Work Permits & Legal Insights

Stay informed about visa types, work permits, and immigration updates for international professionals.

Browse all articles

Subscribe to our newsletter

New visa sponsorship, relocation and remote tech jobs, delivered to your inbox.