Interested in
in this role

Apply now

Deep Learning Deployment Engineer (Cloud)

Passionate about Scaling Hardware Deployment of AI on Cloud ?

We are building the first NO-CODE AI PLATFORM for the AEC industry, with the 3rd generation Explainable AI, that allows users to create complex use cases with zero coding at the frontend and neuro-symbolic AI under the hood.

Tasks

We are looking for a Deep Learning Deployment Engineer (Cloud) to join our Bengaluru office.

You will be part of our product development team and will work closely with other AI Engineers to optimize and deploy AI models on clouds and servers at scale.

  • Optimize AI models (compression, quantization, etc) for deployment on cloud
  • Create dockerized versions of the optimized models
  • Deploying the dockerized models on scalable distributed infrastructure
  • Lifecycle management of the deployed models

The technology will scale in public/private cloud across a rapidly increasing number of customers in multiple geographies, while processing and rendering large amount of based data points.

Requirements

  • B Tech / M Tech in Computer Engineering from a top tier university
  • 5+ years of hands-on experience with Machine Learning & Deep Learning models and their deployment to production on private, hybrid and public clouds
  • Automated creation of dockerized versions of the software
  • Knowledge of AI model optimization techniques (compression, quantization, etc)
  • Experience in designing, building, and running scalabale distributed infrastructure
  • Experienced in Python and Bash scripting
  • Certifications in the field of cloud technologies and solutions like GCP, AWS, AZURE, etc.
  • Design and implementation of concepts/architecture for private, hybrid and multi-cloud scenarios
  • Experience in relational cloud based database technologies and proficiency in SQL
  • Analyze production workloads and develop strategies to run database with scale and efficiency
  • Experience in scaling-up and scaling-out fragmented/distributed databases
  • Experience with all aspects of database security both at infrastructure and application level
  • Knowledge or experience of working basic OS and Networking database related issues.
  • Configuration Management of varied types of deployment environments, specifying compute and memory requirements
  • Monitoring and Analytics such as AWS CloudWatch, BigPanda, GoogleStackDriver
  • Extensive experience in productionization of AI models
  • Experience with Container-Orchestration/Deployment tools such as Kubernetes and/or Docker
  • Knowledge in using popular MLOps frameworks like Kubeflow, MLFlow, and DataRobot
  • Excellent communication skills in English

Benefits

Competitive salary (INR 20L - 28L per annum) depending on the experience

+ Annual Training Budget

+ ESOPs