GenAI SRE Engineer

Orcapod Consulting Services; Hyderabad; Hybrid; INR 4,000,000 - 7,000,000; Full time

Job summary

Orcapod Consulting Services seeks a GenAI SRE Engineer to ensure reliability, availability, and performance of GenAI and LLM platforms in production.

You will bring strong SRE and production ops experience, with hands-on AWS cloud skills, observability tooling, automation, and DR planning.

Qualifications

• Hands-on SRE and production operations experience.
• Experience with AWS cloud services and cloud infrastructure operations.
• Strong knowledge of monitoring and observability.
• Experience with disaster recovery and business continuity.
• Automation scripting with Python or Bash.
• Experience with GenAI/LLM infrastructure reliability.

Responsibilities

• Implement and manage monitoring, observability, logging, and alerting for GenAI systems.
• Design, implement, and maintain disaster recovery strategies and runbooks.
• Monitor and optimize performance, availability, and capacity for GenAI workloads.
• Collaborate with engineering, DevOps, cloud, and platform teams for high reliability.
• Define and track SLIs, SLOs, and SLAs.
• Participate in incident response, RCA, and post-incident reviews.
• Develop automation to reduce manual ops and improve resilience.
• Perform capacity planning and infrastructure optimization.
• Support production deployments and on-call activities.
• Identify and mitigate reliability risks for GenAI and LLM apps.

Skills

SRE

AWS

GenAI

LLM

Python

Bash

Disaster Recovery

Incident Management

Kubernetes

Observability

Education

Bachelor's or Master's degree in Computer Science/IT/Engineering

Tools

Prometheus

Grafana

Datadog

New Relic

ELK Stack

Job description

Job Title: GenAI SRE Engineer

Experience: 68 Years
Job Type: Full-Time
Job Function: Site Reliability Engineering (SRE) / Cloud Operations / GenAI Infrastructure
Mandatory Skill: AWS Cloud
Key Skills: SRE, AWS, GenAI, LLM, Prometheus, Grafana, Datadog, Python, Bash, Disaster Recovery, Incident Management, Kubernetes

Job Summary

We are looking for an experienced GenAI SRE Engineer to ensure the reliability, availability, resilience, and performance of Generative AI (GenAI) systems and Large Language Model (LLM)-based platforms running in production.

The ideal candidate will have strong Site Reliability Engineering (SRE) and production operations experience, hands-on expertise with AWS cloud services, observability, automation, disaster recovery, and a working understanding of GenAI/LLM infrastructure and its operational challenges.

Key Responsibilities

• Implement and manage monitoring, observability, logging, and alerting solutions for GenAI systems and services.
• Design, implement, and maintain disaster recovery (DR) strategies, business continuity plans, and operational runbooks.
• Monitor and optimize system performance, availability, scalability, and resource utilization across GenAI workloads.
• Collaborate with engineering, DevOps, cloud, and platform teams to ensure high availability and reliability of AI services.
• Define, measure, and track Service Level Indicators (SLIs), Service Level Objectives (SLOs), and Service Level Agreements (SLAs).
• Participate in incident response, troubleshooting, root-cause analysis (RCA), and post-incident reviews.
• Develop automation using Python or Bash to reduce manual operational effort and improve platform resilience.
• Perform capacity planning, performance analysis, bottleneck identification, and infrastructure optimization.
• Support production deployments, operational readiness, on-call activities, and continuous reliability improvements.
• Identify and mitigate reliability risks associated with GenAI and LLM-based applications.

Required Skills and Experience

• 68 years of overall IT experience, including hands-on experience in SRE, production support, or infrastructure operations.
• Strong hands-on experience with AWS cloud services and cloud infrastructure operations.
• Experience with observability and monitoring tools such as Prometheus, Grafana, Datadog, New Relic, or ELK Stack.
• Experience designing, implementing, and testing disaster recovery and business continuity solutions.
• Strong understanding of performance monitoring, system tuning, scalability, and capacity planning.
• Proficiency in Python or Bash scripting for automation and operational tooling.
• Working knowledge of Generative AI, LLM infrastructure, and the reliability challenges of AI-powered applications.
• Experience in incident management, production troubleshooting, escalation management, and on-call rotations.
• Strong understanding of SRE principles, high availability, fault tolerance, and production reliability best practices.

Good to Have

• Experience with Kubernetes and containerized deployments for AI/ML workloads.
• Exposure to chaos engineering, fault injection, and resilience testing.
• Familiarity with LLM serving, inference workloads, latency monitoring, and AI platform performance optimization.
• Experience with Infrastructure as Code (Terraform or CloudFormation) and CI/CD pipelines.

Educational Qualifications

Bachelor's or Master's degree in Computer Science, Information Technology, Engineering, or a related discipline.

Preferred Candidate Profile

Candidates with strong AWS, SRE, production operations, observability, disaster recovery, and automation experience, along with exposure to GenAI/LLM platforms, are encouraged to apply.

Keywords: GenAI SRE Engineer, Site Reliability Engineer, AWS SRE, Generative AI, LLM Infrastructure, Cloud Operations, Production Support, Prometheus, Grafana, Datadog, Python, Bash, Kubernetes, Disaster Recovery, Incident Management, SLI, SLO, SLA.