AI Production Support Engineer

Position Name: AI Production Support Engineer
Location: Chennai, Bangalore, Gurugram
Experience: 6-8 years

About BinQle
BinQle is a global delivery and execution partner supporting enterprises across the US, India, Singapore and Australia. We specialize in structured hiring, managed teams, and long-term delivery support.

Role Summary:
Support and operate AI/ML solutions in a regulated banking environment. Ensure high availability, compliance, and risk management for AI systems supporting critical banking services.

What Youll Do:
- Provide L2/L3 production support for AI/ML models and data pipelines in banking systems
- Monitor model performance, drift, data quality, and operational health of AI services
- Ensure stability and uptime of AI platforms for customer-facing and regulatory workloads
- Perform incident management, root cause analysis (RCA), and problem management following ITIL practices
- Collaborate with Data Science, Engineering, Risk, and Compliance teams
- Support secure deployment, release, and rollback of models in production
- Implement monitoring, alerting, and audit logging to meet regulatory and audit requirements
- Ensure adherence to data privacy, governance, and financial regulatory standards
- Support disaster recovery (DR) and business continuity (BCP) plans for AI workloads
- Identify opportunities for automation, operational efficiency, and cost optimisation

What We re Looking For (Must-Haves):
- Experience in production support, SRE, or platform engineering in banking or financial services
- Strong understanding of AI/ML lifecycle and model operations (MLOps)
- Experience with cloud platforms (Azure preferred in banking) and secure workloads
- Proficiency in Python and scripting for debugging and automation
- Hands-on experience with Docker, Kubernetes, and microservices architectures
- Familiarity with MLOps tools (MLflow, Azure ML, SageMaker, etc.)
- Experience with monitoring and observability tools (CloudWatch, Splunk, Grafana, Prometheus)
- Knowledge of data pipelines, APIs, batch and real-time processing systems
- Experience with incident management tools (e.g., ServiceNow)
- Understanding of model risk management (MRM) and audit expectations
- Awareness of data governance, lineage, and controls
- Familiarity with security standards and identity access management (IAM)
- Experience with AWS SageMaker, EC2, EKS, Lambda, S3, CloudWatch
- Experience with SageMaker Pipelines, MLflow, model registry and deployment frameworks
- Experience with Docker and Kubernetes (EKS)
- Experience with AWS CloudWatch, CloudTrail, Prometheus, Grafana, OpenTelemetry
- Experience with AWS CodePipeline, CodeBuild, CodeDeploy, Jenkins, GitHub Actions
- Experience with AWS Glue, Kinesis, EventBridge, REST APIs, SQL/NoSQL (RDS, DynamoDB)
- Experience with IAM, AWS KMS, Secrets Manager, VPC security
- Experience with AWS Backup, cross-region replication, DR strategies (multi-AZ / multi-region)

Good to Have (Optional - only if mentioned):
- Exposure to AI governance frameworks and explainability tools
- Experience with fraud detection, credit risk, or financial analytics models
- Knowledge of secure DevOps (DevSecOps) practices
- Relevant certifications (AWS, MLOps)

Qualifications:
As per requirement

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.