gAIt Onboarding - Senior Platform Reliability Engineer - Generative AI

TIAA is hiring for the position - gAIt Onboarding - Senior Platform Reliability Engineer - Generative AI Infrastructure - Sr. Associate

• Experience - 8 to 12 years
• Location - Mumbai and Pune

Key Duties & Responsibilities :

AI Platform Infrastructure (35%)

Primary Focus Areas:
- Maintain scalable Kubernetes clusters for LLM deployments
- Manage vector store infrastructure (Pinecone/Weaviate/Faiss)
- Optimize DynamoDB performance for high-throughput AI operations
- Configure and maintain S3 data lakes for model artifacts
- Implement efficient model serving architectures

Development Support & Integration (25%)

• Collaborate with ML engineers on model deployment pipelines
• Maintain APIs for model inference services
• Implement A/B testing infrastructure for model variants
• Create developer tooling for model deployment and monitoring
• Support integration of new LLM models into production2

Observability & Performance (20%)

1. Monitoring & Metrics

a. Implement custom metrics for LLM performance

b. Monitor vector store query latencies

c. Track model inference costs

d. Set up distributed tracing for API calls

2. Optimization

a. Tune Kubernetes resources for model serving

b. Optimize vector store query performance

c. Implement caching strategies for frequent queries

d. Manage auto-scaling policies3

Security & Compliance (20%)

• Implement IAM roles and security policies
• Manage API authentication and rate limiting
• Ensure data privacy compliance for AI operations
• Monitor and prevent token/cost abuse
• Implement model access controls

Job Requirements And Qualifications :

• Must have 9-12 Yrs of relevant experience.
• Team Player ability to work in global team environment.
• Collaboration skills with business-driven team, business development and Stakeholder

Technical Requirements

Core Skills

• 5+ years experience with AWS services
• Deep expertise in Kubernetes administration
• Strong Python programming skills
• Experience with Infrastructure as Code (Terraform)
• Understanding of ML/LLM deployment patterns

Required AWS Experience

• Primary Services:
  - EKS (Kubernetes)
  - S3 & DynamoDB
  - VPC & Networking
  - IAM & Security
  - CloudWatch & Monitoring
  - API Gateway
  
  

AI Infrastructure Experience

• Vector database deployment
• LLM serving frameworks
• API development and gateway management

Licenses/Certifications

• AWS Certified DevOps / Solutions Architect
• CKA Certified.