Tuesday, June 30, 2026

AI Site Reliability Engineer for Tampa, FL (Onsite)

Hi,

My name is Rohit Chauhan, and I am a Staffing Specialist at Novia Infotech LLC. I am reaching out to you on an exciting job opportunity with one of our clients.

 

Job Title: AI Site Reliability Engineer (SRE) – Generative AI Systems

Location: Tampa, FL (Onsite)

Position Overview

We are seeking a highly skilled AI Reliability Engineer (SRE) – Generative AI Systems to join our Application Engineering team. This role combines expertise in Software Engineering, Cloud Infrastructure, DevOps, Machine Learning Operations (MLOps), and Site Reliability Engineering (SRE) to build and maintain scalable, highly available Generative AI platforms.

The ideal candidate will be responsible for ensuring the reliability, performance, security, and scalability of Large Language Model (LLM) infrastructure while designing autonomous AI-driven workflows that automate operational tasks, incident management, and system remediation.

Key Responsibilities

AI Infrastructure Reliability

  • Design, implement, and maintain highly available infrastructure supporting LLM training, fine-tuning, and inference workloads.
  • Ensure scalability, resiliency, and operational excellence of AI platforms in cloud environments.

Agentic AI Operations

  • Architect and deploy multi-agent Generative AI systems to automate:
    • Alert triage
    • Root Cause Analysis (RCA)
    • Incident response
    • Self-healing remediation workflows
  • Convert operational runbooks into autonomous executable workflows.

GPU & Kubernetes Cluster Management

  • Optimize GPU resource allocation and orchestration across large-scale Kubernetes environments.
  • Monitor cluster health, capacity planning, and compute utilization.
  • Improve infrastructure efficiency and workload scheduling.

AI Performance Monitoring

  • Define and manage AI-specific Service Level Indicators (SLIs) and Service Level Objectives (SLOs), including:
    • Time-to-First-Token (TTFT)
    • Inter-Token Latency
    • Throughput
    • Cost-per-query metrics
  • Drive continuous optimization of AI system performance.

Data & Vector Pipeline Operations

  • Manage and maintain vector databases and Retrieval-Augmented Generation (RAG) pipelines.
  • Ensure reliability, synchronization, low latency, and data consistency across distributed AI systems.

Incident Management & ChatOps

  • Integrate LLMs and AI agents into ChatOps platforms such as Slack and Microsoft Teams.
  • Provide real-time, natural-language incident analysis and operational assistance.
  • Automate incident resolution workflows.

Security & AI Guardrails

  • Implement security controls and governance mechanisms to protect AI systems from:
    • Prompt injection attacks
    • Hallucinations
    • Data leakage
    • Compliance violations
  • Establish robust operational guardrails for enterprise AI environments.

Required Qualifications

Infrastructure & DevOps

  • Strong experience with:
    • Kubernetes (EKS, GKE)
    • Infrastructure as Code (Terraform)
    • CI/CD pipelines
    • Cloud-native architectures

Software Engineering

  • Strong programming experience in:
    • Python
    • Go
  • Experience building integrations through APIs and Model Context Protocol (MCP).

Generative AI Engineering

  • Hands-on experience with:
    • LangChain
    • AutoGen
    • LlamaIndex
    • LLM orchestration frameworks
  • Experience developing and deploying agentic AI systems.

Data & Vector Databases

  • Experience with distributed vector databases such as:
    • Pinecone
    • Milvus
    • Qdrant
    • pgvector

Observability & Monitoring

  • Expertise in:
    • Datadog
    • Prometheus
    • OpenTelemetry
    • AI workload monitoring tools
    • Triton Inference Server monitoring

Preferred Qualifications

  • Experience implementing semantic caching solutions to reduce API and cloud token costs.
  • Knowledge of MLOps best practices and AI infrastructure optimization.
  • Experience building autonomous AI agents for operational automation.
  • Strong understanding of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and AI observability.
  • Proven ability to transform traditional operational runbooks into automated agent workflows.

 

Rohit Chauhan

IT Recruiter

E: rohit.c@noviainfotech.com

www.noviainfotech.com

A: 4421 Avenida Ln, McKinney, TX, 75070

 

 

 

 

--
You received this message because you are subscribed to the Google Groups "NoviaJobs" group.
To unsubscribe from this group and stop receiving emails from it, send an email to noviajobs+unsubscribe@googlegroups.com.
To view this discussion visit https://groups.google.com/d/msgid/noviajobs/CAJ0-OE9Q_SgiiktAZdmF%3D88dF5ggFctbTGX9cLMbR2U6f8CQzQ%40mail.gmail.com.

No comments:

Post a Comment

Hiring for Lead Data Scientist – AI/ML for Cary, NC (Locals Only - F2F)

Hi, Local candidates Job Title: Lead Data Scientist – AI/ML & Generative AI Location: Cary, NC (Onsite) Duration: 12...