Description
You will lead the development and deployment of scalable AI/ML infrastructure and agentic systems.
Responsibilities
- Build and maintain high-concurrency, scalable systems using asynchronous and event-driven programming.
- Design and implement CI/CD pipelines using GitHub Actions, AWS CodePipeline, and CodeBuild.
- Integrate LLMs and AI/ML solutions into production workflows, including multi-step agentic systems.
- Manage container orchestration using Kubernetes and EKS.
- Develop microservices and REST APIs to support retrieval systems and ML workflows.
Required Skills
- 3+ years of Python development experience.
- Hands-on experience with AWS infrastructure.
- Proficiency with Kubernetes and EKS.
- Experience with CI/CD tools: GitHub Actions, AWS CodePipeline, and CodeBuild.
- Knowledge of LLM integration and agentic, multi-step workflows.
- Strong background in event-driven and asynchronous programming.
- Experience developing microservices and REST APIs.
- Experience with retrieval systems such as OpenSearch.
- Proven ability to build high-concurrency, scalable systems.
Preferred Skills
- Proficiency with FastAPI and Celery.
- Experience with the AWS stack: Redis, DynamoDB, S3, SQS, Kinesis, KMS, IAM, and Secret Manager.