Logo for HyrEzy Talent Solutions LLP

MLOps / AI Infrastructure Engineer

HyrEzy Talent Solutions LLP

Role overview

Qualifications

  • 4–8 years of experience in cloud infrastructure, DevOps, or backend engineering with a focus on ML systems
  • Deep proficiency in Python, Docker, Kubernetes, Terraform, and cloud platforms (AWS Bedrock, SageMaker, GCP Vertex AI, or similar)
  • Hands-on familiarity with vector databases (Pinecone, Milvus, Qdrant) and LLM orchestration frameworks

Responsibilities

  • Architect and maintain scalable model deployment pipelines for LLMs, deep learning models, and predictive analytics engines using tools like Triton, Ray, or BentoML
  • Build automated CI/CD pipelines for machine learning covering data ingestion, feature stores, model training, validation, and monitoring
  • Monitor GPU/CPU cluster utilization, manage container orchestration (Kubernetes), and optimize cloud compute expenditures for heavy AI workloads
  • Work closely with Data Scientists and AI Researchers to transition experimental models into resilient, low-latency production services

Key facts

Hard skills

Other skills

  • Collaboration

About the company

HyrEzy Talent Solutions LLP logo

HyrEzy Talent Solutions LLP

Human Resources Services

HyrEzy Talent Solutions Delivers exceptional service to both client and candidate. We have a proven track record and are renowned for our high level success. Because of our outstanding performance, we are the exclusive recruitment company used by a number of our clients. We keep abreast with the latest technology and adapt to the ever changing needs in the marketplace.Specializes in permanent staffing services, Our goal is to provide a service that places our clients’ needs as well as our candidate's career. Not simply providing an ad-hoc recruitment source, but a methodical and complete recruitment solution within all industries.We have Team of Recruiters working for us Pan India. Handle Requirements across sectors like IT, Healthcare, eCommerce, Retails, Wellness, Fitness, Fashion, Banking and Financial Services etc. We can cater recruitment in any sector across any Level.Dedicated and expert team, which works across diverse industry verticals with very short Turn Around Times with a decent conversion ratio. 30 days Guaranteed DeliveryFixed Fee StructureOur top team to handle hiring for start upsMarket Research for checking on the viability of start-upsRight talent for StartupsBrand Selling for StartupsCompensation Analysis for recruitment for the startupsCatering Recruitment services to Technology Startups in Healthcare, BFSI, Energy and E-Commerce Verticals. Recent Hires for our clients : Strategy HeadCTO, Tech Lead, Full Stack Engineer, Front End Developer, Back End Developer, Android & iOS Developer, Java Programmer, Node.js Programmer, Product Managers, VP Category Management, UI Designer, UX Designer, Business Head, Digital Marketing Manager, Creative Director, Sales Director, Content Editors/Writers, SEO Managers, SEM HeadCity Head

Company details

IndustryHuman Resources Services
Company size11 - 50

Links

LinkedIn See all jobs

Your match analysis

See how your profile stacks up against this role.

We compared the job requirements to your profile to show where you're strong and where you fall short.

Job description

  • Experience Range: 4–8 Years | Location: Bangalore / Remote

Position Overview

As an MLOps and AI Infrastructure Engineer, you sit at the intersection of software engineering, data science, and cloud operations. You will be responsible for building, scaling, and optimizing the underlying pipelines, model-serving architectures, and infrastructure required to run large-scale machine learning and generative AI workloads efficiently in production.

Key Responsibilities & Scope

  • Model Deployment & Serving: Architect and maintain scalable model deployment pipelines for LLMs, deep learning models, and predictive analytics engines using tools like Triton, Ray, or BentoML.

  • Pipeline Automation: Build automated CI/CD pipelines for machine learning (ML pipelines) covering data ingestion, feature stores, model training, validation, and monitoring.

  • Infrastructure Cost & GPU Optimization: Monitor GPU/CPU cluster utilization, manage container orchestration (Kubernetes), and optimize cloud compute expenditures for heavy AI workloads.

  • Collaboration: Work closely with Data Scientists and AI Researchers to transition experimental models into resilient, low-latency production services.

Must-Have Qualifications

  • Experience: 4–8 years of experience in cloud infrastructure, DevOps, or backend engineering with a heavy focus on ML systems.

  • Tech Stack: Deep proficiency in Python, Docker, Kubernetes, Terraform, and cloud platforms (AWS Bedrock, SageMaker, GCP Vertex AI, or similar).

  • Domain Expertise: Hands-on familiarity with vector databases (Pinecone, Milvus, Qdrant) and LLM orchestration frameworks.

Apply once. Then go straight to the hiring manager.

After you apply, unlock the direct contact details of the people who actually make the call. A quick follow-up makes you 5x more likely to land an interview.

MR

Marcus Rivera

Chief Revenue Officer

m.rivera@company.com
linkedin.com/in/marcusrivera
Unlocked after you apply
·

Infrastructure Engineer Related jobs

Other jobs at HyrEzy Talent Solutions LLP

Premium

Reach out to the hiring manager directly.

Gain access to the contact details of the hiring managers who actually decide, and reach out to network with them directly. That, plus more when you upgrade:

  • Full match report with fit score and gaps
  • Career diagnostics on how recruiters read you
  • Curated company matches and warm intros
  • 48h early access to new roles

Cancel anytime.