M
MSD•6h ago
Indeed

Specialist

Hyderabad, Telangana
Full Time
Mid Level

Auto Apply to 50+ AI Matched Specialist Jobs

Use Auto Apply Agents to Bulk Apply jobs with ATS Optimised Resumes, find verified Insider Connections for jobs at MSD

Full Job Description

Specialist, Site Reliability Engineering

The Opportunity: Based in Hyderabad (Hyderabad, Telangana), join MSD to be part of a team using data and analytics to tackle some of the world's greatest health threats.

Role Overview

You keep the inference platform running. You build monitoring, alerting, capacity dashboards, incident handling, and automation that lets a small team support production models reliably.

What will you do in this role:

  • Build observability for the inference layer (GPU to gateway): GPU health/utilisation (DCGM, XID/ECC errors), engine metrics (time to first token, inter-token latency, queue depth, KV cache use, etc.).
  • Run synthetic end-to-end probes checking model response content.
  • Create capacity and status dashboards showing run locations and free capacity.
  • Implement SLOs, error budgets, alerts; manage on-call/incident response;
  • Handle incidents/problems via IT service management (ServiceNow).
  • Automate operations: health checks, self-healing, safe upgrades, traffic spill-over signals. Coordinate node draining with hardware/cluster teams.
  • Run capacity/resilience tests; keep runbooks up to date.
  • Collaborate on hardware faults, cluster issues, and security/logging access.

What you should have

  • Bachelor's degree in IT, Computer Science, or related field.
  • 3 to 6 years of hands-on experience working in full-stack development.
Primary Skills (Must Have):
  • SRE / DevOps / Platform Engineering
  • Prometheus & Grafana (or equivalent)
  • Kubernetes Administration Operations
  • Linux System Administration / Operations
  • Python or Bash Scripting for automation
  • LLM Serving Engines: vLLM, SGLang, or Triton
  • Infrastructure as Code (IaC) & CI/CD Pipelines
Secondary Skills (Nice to have):
  • Operating GPU clusters (NVIDIA DCGM/GPU Operator) or HPC environments.
  • Cybersecurity: security monitoring, Kubernetes security (RBAC), vulnerability management.

Company

M

MSD

MSD is a global healthcare biopharma company with over 130 years of legacy, driven by ethical integrity and an inspiring mission to achieve new milestones in global healthcare.We operate as Merck Co.,...

Hyderabad, Telangana
Posted on Indeed

Practice this interview

A voice mock interview for Specialist, Site Reliability Engineering at MSD, with questions from this job description and your resume, and a scored report afterwards.

Set up interview