Hi All,
Greetings!
We're hiring for AGS for the role AI Ops Engineer for more quires kindly reach out -
[email protected]
ROLE: AI Ops Engineer
EXP: 3 Yrs
LOC: Bangalore
NP: 0 to 30 Days
JD for your reference
AIOps Engineer, AI Foundation (LLMOps / Orchestration)
Department: Engineering
Location: Bangalore
Employment Type: Full time
About the Role
Own the reliable, scalable, and compliant operation of the AI/LLM platform in production. You will run model orchestration and the model gateway/serving layer across multiple providers (AWS Bedrock and others), CI/CD for models and prompts, platform observability, and cost/latency instrumentation - keeping the runtime healthy, auditable, and cheap to run for both the RCM and coding-AI teams.
Key Responsibilities
- Own and manage model orchestration and the model gateway/serving layer across AI providers (Bedrock and others).
- Build and maintain CI/CD pipelines for models, prompts, and AI services - including versioning, rollout, and rollback.
- Monitor platform health through tracing, metrics, logging, alerting, and dashboards.
- Track and drive down cost-per-transaction, throughput, and latency for AI workloads.
- Ensure runtime compliance, auditability, and secure handling of PHI/PII in production.
- Support production deployment and incident resolution for AI workloads across both verticals.
Required Qualifications
- 2 years overall in software, DevOps, or MLOps engineering, with 1-2 years hands-on operating AI/ML or LLM systems in production.
- Hands-on experience with LLMOps/MLOps concepts and the AI model lifecycle.
- Experience with AWS Bedrock, model gateways, or multi-model orchestration.
- CI/CD pipelines for AI/ML applications (GitHub Actions, Jenkins, or GitLab CI).
- Strong grasp of model/prompt versioning, rollout, and rollback strategies.
- Observability tooling for tracing, logging, metrics,
and alerting (Prometheus, Grafana, OpenTelemetry, CloudWatch, or equivalent).
- Proficiency with Python and API-based integrations, on a major cloud (AWS preferred).
- Working knowledge of cost optimization, latency monitoring, and performance instrumentation for AI workloads.
Preferred Qualifications
- PHI/PII handling, healthcare data compliance, and audit readiness; exposure to HIPAA, GDPR, or similar frameworks.
- LLM serving frameworks, vector databases, and AI gateway platforms.
- Kubernetes, Docker, and containerized deployments.
- Agentic AI and workflow orchestration tools (LangGraph, LangChain, Semantic Kernel, or equivalent).
- Familiarity with security, governance, and responsible-AI practices.
Technology & Tools
- Languages: Python (primary); shell and API-based integration.
- Orchestration/serving: AWS Bedrock, model gateway/router patterns, multi-model orchestration; LangGraph / LangChain / Semantic Kernel a plus.
- CI/CD: GitHub Actions, Jenkins, or GitLab CI for models, prompts, and services.
- Observability: Prometheus, Grafana, OpenTelemetry, or CloudWatch for tracing, metrics, logging, and alerting.
- Cloud/infra: AWS (compute, IAM, networking); Docker and Kubernetes for containerized deployment.
- Data/retrieval: vector databases and LLM serving frameworks (a plus).
Education
Bachelor's degree in Computer Science, Engineering, or a related field
Certifications
No certification required. AWS certifications (e.g., AWS Certified DevOps Engineer, Solutions Architect - Associate, or Machine Learning - Specialty) are a plus.
Relevant Background
3 years in software, DevOps, or MLOps engineering - with recent hands-on operation of AI/ML or LLM systems in production - at a health-tech, RCM/claims technology, applied-AI, or cloud-platform company. Experience running a shared or multi-team platform (not only a single application) is preferred.
Regards
Divya
📌 AI Ops Engineer (Bengaluru)
🏢 AGS Health
📍 Bengaluru