LLMOps DevOps Engineer

Hi,

PFB Job description and kindly connect and let me know if interested or Share your CV on [email protected] or if you have any references it will be helpful.

Responsibilities:

• Collaborate with LLM Engineers, Cloud/Platform teams, Security, Risk, and Networking teams to produce GenAI solutions.
• Design, implement, and manage infrastructure for LLM-powered applications including RAG pipelines, agent frameworks, and copilots.
• Architect secure and scalable cloud networking solutions including VNET/VPC design, subnets, private endpoints, DNS configuration, and network security controls.
• Configure and manage network security components such as NSGs, firewalls, load balancers, ingress controllers, and API gateways.
• Ensure secure connectivity between services using Private Endpoints, VPNs, ExpressRoute/Direct Connect, and hybrid networking models where applicable.
• Build and maintain CI/CD pipelines for ML and LLM workloads using modern DevOps practices.
• Deploy, monitor, and manage LLM endpoints (Azure OpenAI/OpenAI APIs) in secure enterprise environments.
• Implement containerization and orchestration strategies using Docker and Kubernetes (AKS preferred), including cluster networking and service mesh configurations.
• Develop infrastructure as code (IaC) using Terraform for scalable and repeatable deployments.
• Establish robust monitoring, logging, and observability frameworks using OpenTelemetry, Azure Monitor, App Insights, Datadog, and structured logging practices.
• Manage vector databases such as Azure AI Search, Pinecone, Elastic, or OpenSearch for retrieval systems.
• Implement model lifecycle management, evaluation frameworks, and automated validation pipelines.
• Ensure Responsible AI enforcement, governance controls, and compliance with enterprise security and networking standards.
• Implement secure authentication and access mechanisms using Key Vault, Managed Identity, RBAC, and network isolation principles.
• Perform load and performance testing using tools such as K6, Postman, or JMeter.
• Optimize infrastructure and networking configurations for cost, scalability, reliability, and low latency.
• Stay updated with advancements in LLMOps, DevOps automation, cloud-native networking, and security technologies to enhance enterprise GenAI platforms.

Requirements:

• Bachelors or Master’s degree in Computer Science, Information Technology, Engineering, or a related field.
• 4–6+ years of experience in DevOps, MLOps, Platform Engineering, Cloud Engineering, or Infrastructure Engineering roles.
• Hands-on experience operationalizing ML or LLM systems in production environments.
• Strong programming skills in Python and/or Bash. Familiarity with TypeScript or Java is a plus.
• Experience building and managing CI/CD pipelines using GitHub Actions or Azure DevOps Pipelines.
• Proficiency in containerization and orchestration technologies such as Docker and Kubernetes (AKS preferred).
• Strong understanding of cloud networking concepts including VNET/VPC architecture, subnetting, routing, DNS, load balancing, firewalls, and private connectivity.
• Experience implementing secure networking patterns such as Private Endpoints, VPNs, ExpressRoute/Direct Connect, and zero-trust architecture.
• Experience working with cloud platforms (Azure preferred; AWS/GCP acceptable).
• Experience implementing monitoring, logging, and observability solutions in enterprise systems.
• Familiarity with vector databases and LLM deployment patterns (RAG architectures).
• Understanding of Responsible AI principles, model governance, data privacy, enterprise security, and compliance controls.
• Strong troubleshooting skills across infrastructure, networking, and application layers.
• Excellent communication and collaboration abilities.
• Ability to work in a fast-paced, dynamic environment supporting production-grade AI systems.

Nice to Have Skills:

• Experience with Azure OpenAI, OpenAI APIs, and model deployment endpoints.
• Familiarity with orchestration frameworks such as LangChain, LangGraph, or Semantic Kernel.
• Experience supporting enterprise AI governance, compliance programs, and secure network architectures.
• Healthcare domain understanding would be an added advantage
• Certifications

If you are passionate about building scalable, secure, and network-resilient GenAI platforms and have strong DevOps expertise, join PwC US – Acceleration Center and be part of a team that is operationalizing enterprise Generative AI at scale. We offer a collaborative and innovative environment where you can make a significant impact on next-generation AI systems.

Preferred Qualifications:

• BE / B.Tech / MCA / M.Sc / M.E / M.Tech / Master’s Degree from a reputed institute