HamburgerMenu
hirist

Job Description

Role : Infrastructure Engineer - L3

Location : Hyderabad, Telangana

Role Overview :

Own infrastructure architecture, scalability, and reliability. Set technical direction, define SRE practice, and mentor engineers. Build and operate AI-scale infrastructure powering real-time healthcare workflows.

Key Responsibilities :

Architecture & Platform :

- Design scalable, secure, cost-efficient AWS/GCP architectures for AI and healthcare workloads.

- Lead IaC standards and reusable modules org-wide; own GitOps practices.

- Architect optimized Kubernetes (EKS/GKE) for HA, scale, and GPU workload orchestration.

Reliability Engineering :

- Define and drive reliability targets (SLOs/SLIs); establish SRE practice.

- Lead incident management, RCA, and blameless post-mortems for critical systems.

- Partner on infrastructure hardening and compliance (SOC 2, HIPAA).

AI-First Engineering :

- Lead AI/ML inference and GPU infrastructure scaling in production.

- Evaluate and introduce AI tooling, platforms, and automation best practices.

- Contribute to LLM deployment pipelines and AI systems reliability.

Leadership & SDLC :

- Mentor L1/L2 engineers; influence cross-team infrastructure decisions.

- Drive DevSecOps maturity across the SDLC (policy-as-code, SBOM, supply-chain security).

- Evaluate and introduce new tooling and platforms.

Requirements :

- 4 - 7 years infrastructure/platform/DevOps/SRE.

- Deep expertise in AWS & GCP large-scale production systems.

- Advanced Kubernetes (cluster design, multi-tenant ops, resource quotas).

- AI/ML inference or GPU infrastructure scaling (production track record).

- Strong Terraform / equiv. and GitOps practices.

- Python, Go, or Bash scripting and automation.

- Track record in scale, reliability, and cost efficiency.

- Lead incident response and on-call practices.

Nice-to-Have :

- LLM Gateway architecture and optimization.

- Zero-trust networking and advanced security/compliance (SOC 2, HIPAA).

- DevSecOps maturity : SBOM, supply-chain security, policy-as-code.

- Open-source contributions or platform-team leadership.

Interview Process : Recruiter Screen - Functional / Technical Round - System Design / Product Deep Dive - Founder Interview

info-icon

Did you find something suspicious?

Similar jobs that you might be interested in

Loading chat...