AI Ops Engineer

Antal International; Bengaluru; On-site; INR 1,400,000 - 2,400,000; Full time

Job summary

Antal International in Bengaluru is seeking an AIOps Engineer to join the AI Foundation team and scale the AI/LLM production platform. You will own multi-model serving layers and orchestration across providers like AWS Bedrock.

The role emphasizes CI/CD pipelines for model/version control, observability with OpenTelemetry, Grafana and Prometheus, and secure handling of PHI/PII data in production AI ecosystems. This is an on-site, office-based role in Bangalore.

Qualifications

• 2+ years overall in DevOps/MLOps/Software Engineering.
• 1–2 years hands-on with production LLM/AI systems.
• Proficient in Python and AWS Bedrock, Docker and Kubernetes.

Responsibilities

• LLM gateway and orchestration across multiple models and providers, including AWS Bedrock.
• AI CI/CD pipelines for versioning, rollout, and rollback of models and microservices.
• Observability and performance: tracing, logging, and alerting with OpenTelemetry, Grafana, and Prometheus.
• Ensure secure handling of PHI/PII data in production AI systems.

Skills

DevOps/MLOps

Python

AWS Bedrock

Docker

Kubernetes

GitHub Actions

GitLab CI

CI/CD

OpenTelemetry

Grafana

Prometheus

Security/Compliance

Tools

GitHub Actions

GitLab CI

OpenTelemetry

Grafana

Prometheus

Job description

Are you passionate about building robust, scalable infrastructure for cutting-edge Generative AI? We’re looking for an AIOps Engineer to join our AI Foundation team in Bangalore to own and scale our AI/LLM production platform!

Mode:

Work from office

Responsibilities:

• LLM Gateway & Orchestration: Own multi-model serving layers and orchestration across providers like AWS Bedrock.
• AI CI/CD: Build pipelines for seamless versioning, automated rollouts, and rollbacks of models, prompts, and AI microservices.
• Observability & Performance: Drive end-to-end tracing, logging, and alerting (OpenTelemetry, Grafana, Prometheus) while optimizing transaction costs and latency.
• Compliance & Security: Ensure secure handling of PHI/PII data in a production AI ecosystem.

Requirements:

• Experience: 2+ years overall in DevOps/MLOps/Software Engineering, with 1–2 years hands-on with production LLM/AI systems.
• Tech Stack: Python, AWS (Bedrock, IAM, Compute), Docker/Kubernetes, GitHub Actions / GitLab CI.