Posted 22 August, 2026
Infra Support Engineer
APN Consulting
Bengaluru,Karnataka,India
Full Time
Reference: 365_625625_26-12598
APN Consulting, Inc. is a progressive IT staffing and services company offering innovative business solutions to improve client business outcomes. We focus on high impact technology solutions in ServiceNow, Fullstack, Cloud & Data, and AI / ML. Due to our globally expanding service offerings we are seeking top-talent to join our teams and grow with us.
Role: Infra Support Engineer
Mode: Remote
Position: Permanent OR C2H
Shift: Rotational Shift (24*7)
Key Responsibilities:
We are committed to fostering a diverse, inclusive, and equitable workplace where individuals from all backgrounds feel valued and empowered to contribute their unique perspectives. We strongly encourage applications from candidates of all genders, races, ethnicities, abilities, and experiences to join our team and help us build a culture of belonging.
Role: Infra Support Engineer
Mode: Remote
Position: Permanent OR C2H
Shift: Rotational Shift (24*7)
Key Responsibilities:
- Deploy, manage, and optimize AI/ML and LLM inference workloads across GPU clusters, HPC infrastructure, and cloud environments.
- Build and maintain scalable AI platform infrastructure using Kubernetes, containers, and enterprise orchestration platforms.
- Administer and optimize Linux servers including system configuration, patching, security hardening, performance tuning, and troubleshooting.
- Manage physical infrastructure including servers, storage, networking, and bare-metal environments within enterprise data centers.
- Implement and maintain CI/CD and automation workflows for platform and infrastructure deployments.
- Optimize infrastructure performance, GPU utilization, resource allocation, and distributed workloads to meet operational requirements.
- Benchmark and evaluate AI workloads for scalability, latency, throughput, and resource efficiency.
- Collaborate with infrastructure, SRE, and platform engineering teams to provision compute resources and maintain enterprise-scale AI environments.
- Implement monitoring, logging, observability, and alerting solutions for platform reliability and operational visibility.
- Apply security patches, upgrades, compliance controls, and operational best practices for Linux and Kubernetes environments.
- Troubleshoot issues across hardware, networking, operating systems, Kubernetes clusters, and AI/ML workloads.
- Support enterprise operations through efficient incident, change, and ticket management processes.
- Automate infrastructure operations using scripting and infrastructure automation tools.
- 8+ years of experience in Linux systems administration, cloud-native infrastructure, HPC environments, or platform engineering.
- At least 4 years of experience supporting AI/ML workloads or large-scale distributed compute environments in production.
- Comfortable leveraging AI-assisted tools for collaborative development, code generation, refactoring, and productivity enhancement.
- Strong hands-on expertise with Linux administration (RHEL, Ubuntu, or similar).
- Experience with Kubernetes administration, container orchestration, and cloud-native infrastructure platforms.
- Strong understanding of GPU infrastructure, distributed computing, and HPC systems.
- Hands-on experience with bare-metal infrastructure, servers, storage systems, and enterprise networking.
- Strong understanding of networking fundamentals including TCP/IP, DNS, load balancing, and firewalls.
- Experience with scripting and infrastructure automation with Bash, Python etc.
- Experience with CI/CD, DevOps, or infrastructure deployment workflows.
- Experience with monitoring, observability, and logging platforms.
- Strong troubleshooting and performance optimization skills across Linux, Kubernetes, networking, and infrastructure stacks.
- Excellent problem-solving, communication, and collaboration skills.
- Ability to work effectively in fast-paced, mission-critical production environments.
- Experience with OpenShift or large-scale Kubernetes platform operations.
- Hands-on experience supporting AI/ML and LLM inference platforms at scale, including working with vLLM for high-performance LLM serving, optimization, and large-scale inference.
- Experience with infrastructure-as-code, GitOps, or advanced automation frameworks.
- Proficiency with Python, Bash, Ansible, Jenkins, Git, ArgoCD, or similar DevOps tooling.
- Experience with GPU performance tuning, distributed AI workloads, or HPC optimization.
- Familiarity with observability platforms such as Prometheus, Grafana, ELK/Elasticsearch, or distributed tracing systems.
- Experience supporting enterprise AI infrastructure in hybrid cloud or large-scale data center environments.
- Familiarity with Juniper networking environments or enterprise network operations.
- RHCSA/RHCE, CKA/CKS, or similar infrastructure/platform certifications
We are committed to fostering a diverse, inclusive, and equitable workplace where individuals from all backgrounds feel valued and empowered to contribute their unique perspectives. We strongly encourage applications from candidates of all genders, races, ethnicities, abilities, and experiences to join our team and help us build a culture of belonging.
