MLOps Engineer
Build and maintain the infrastructure that powers our AI systems. We need someone who can bridge the gap between ML models and production systems at scale.
What You'll Do
Design and implement ML pipelines for training, evaluation, and deployment
Build and maintain inference infrastructure for low-latency, high-throughput serving
Implement monitoring and observability for ML systems — tracking model performance, data drift, and system health
Manage vector databases and embedding infrastructure for RAG systems
Optimize compute costs while maintaining performance requirements
Implement CI/CD pipelines for model deployment and rollback
Collaborate with ML engineers to productionize research code
Ensure security and compliance of ML infrastructure
What We're Looking For
Essential Requirements
4+ years of experience in DevOps, SRE, or infrastructure engineering
2+ years working with ML systems in production
Strong experience with cloud platforms (AWS, GCP, or Azure)
Proficiency in containerization and orchestration (Docker, Kubernetes)
Experience with ML serving frameworks (TensorFlow Serving, Triton, vLLM)
Strong Python skills and familiarity with ML libraries
Experience with infrastructure-as-code (Terraform, Pulumi)
Understanding of ML lifecycle and model deployment patterns
Preferred Qualifications
Experience with LLM inference optimization and serving
Knowledge of vector databases (Pinecone, Weaviate, Qdrant)
Familiarity with ML experiment tracking (MLflow, Weights & Biases)
Experience with GPU infrastructure and optimization
Understanding of model monitoring and drift detection
Experience with data pipeline tools (Airflow, Dagster)
Knowledge of edge deployment and model optimization
Relevant certifications (AWS ML Specialty, GCP ML Engineer)
Benefits & Perks
Competitive salary with equity options
Comprehensive health and accidental insurance
Flexible remote work arrangement
Provident Fund (PF) and gratuity benefits
Professional certification budget
Access to cloud resources and cutting-edge infrastructure
Generous leave policy
Conference and training opportunities
Collaborative team of ML and infrastructure experts
Opportunity to build ML infrastructure at scale
Join Our Infrastructure Team
Our Infrastructure team builds the foundation that makes AI work at scale. We're the team that takes ML models from notebooks to production, ensuring they run reliably, efficiently, and securely. You'll work with cutting-edge ML infrastructure — from LLM serving to vector databases to real-time inference pipelines. We value reliability, efficiency, and elegant solutions to hard problems.
Ready to Build ML Infrastructure?
Join us in building the infrastructure that powers production AI systems.