Senior Infrastructure Engineer - GenAI

Key Responsibilities:

• Design and implement scalable backend services and APIs for generative AI applications using microservices architecture and cloud-native patterns.

• Build and maintain model serving infrastructure with load balancing, auto-scaling, caching, and failover capabilities for high-availability AI services.

• Deploy and orchestrate containerized AI workloads using Docker, Kubernetes, ECS, and OpenShift across development, staging, and production environments.

• Develop serverless AI functions using AWS Lambda, ECS Fargate, and other cloud services for scalable, cost-effective inference.

• Implement robust CI/CD pipelines for automated deployment of AI services, including model versioning and gradual rollout strategies.

• Create comprehensive monitoring, logging, and alerting systems for AI service performance, reliability, and cost optimization.

• Integrate with various LLM APIs (OpenAI, Anthropic, Google) and open-source models, implementing efficient batching and optimization techniques.

• Build data pipelines for training data preparation, model fine-tuning workflows, and real-time streaming capabilities.

• Ensure adherence to security best practices, including authentication, authorization, API rate limiting, and data encryption.

• Collaborate with AI researchers and product teams to translate AI capabilities into production-ready backend services.

Required Technical Skills:

• Strong experience with backend development using Python, with familiarity in Go, Node.js, or Java for building scalable web services and APIs.

• Hands-on experience with containerization using Docker and orchestration platforms including Kubernetes, OpenShift, and AWS ECS in production environments.

• Proficient with cloud infrastructure, particularly AWS services (Lambda, ECS, EKS, S3, RDS, ElastiCache) and serverless architectures.

• Experience with CI/CD pipelines using Jenkins, GitLab CI, GitHub Actions, or similar tools, including Infrastructure as Code with Terraform or CloudFormation.

• Strong knowledge of databases including PostgreSQL, MongoDB, Redis, and experience with vector databases for AI applications.

• Familiarity with message queues (RabbitMQ, Apache Kafka, AWS SQS/SNS) and event-driven architectures.

• Experience with monitoring and observability tools such as Prometheus, Grafana, DataDog, or equivalent platforms.

• Knowledge of AI/ML model serving frameworks like MLflow, Kubeflow, TensorFlow Serving, or Triton Inference Server.

• Understanding of API design principles, load balancing, caching strategies, and performance optimization techniques.

• Experience with microservices architecture, distributed systems, and handling high-traffic, low-latency applications.