- Growing fastShowed strong hiring growth in the past month
Sr. Backend Engineer – MLOps/DevOps
- ₹18L – ₹24L • No equity
- 2 years of exp
- Full Time
Not Available
In office
Vaibhav Nandwani
About the job
As a Backend Engineer, you will be at the forefront of developing the infrastructure that powers our state-of-the-art transformer diffusion models and generative AI capabilities. Your work will involve building and optimizing scalable, high-performance systems capable of serving cutting-edge machine learning models to millions of users. You’ll collaborate closely with our research team to prototype, build, and deploy advanced inference pipelines across thousands of GPUs.
Key Responsibilities:
- Develop and maintain robust backend systems, including REST APIs, for large-scale generative AI models.
- Design and optimize inference pipelines for efficient deployment and scaling of transformer diffusion models.
- Manage and monitor infrastructure across cloud platforms like AWS, Azure, or GCP to ensure reliable and secure AI model serving.
- Collaborate with the research team to integrate new AI models and optimize their performance in production.
- Ensure the security and authentication of the infrastructure to protect data and model integrity.
Competencies:
- Proficiency in Python: Strong skills in Python for backend development and data processing.
- API Development: Experience in designing and deploying high-traffic RESTful APIs.
- Cloud Infrastructure: Hands-on experience with cloud platforms such as AWS, Azure, or GCP for deploying and managing machine learning models.
- Scalability and Optimization: Understanding of scalable backend systems and experience in optimizing performance for real-time applications.
- Security: Knowledge of best practices in security and authentication for cloud-based infrastructures.
Experience:
- 2+ Years of Industry Experience: Proven track record as a software engineer in backend development and infrastructure, particularly in AI/ML environments.
- High-Traffic Systems: Experience in building and managing high-performance, scalable systems for serving machine learning models at scale.
Note: This role is not suitable for recent graduates. We are looking for candidates with a minimum of 2 years of relevant industry experience. Also candidate should be willing to move to Mumbai
About the company
Asynq AI
- Growing fastShowed strong hiring growth in the past month