MLOps Engineer

‍

We are looking for an MLOps Engineer with strong experience in deploying, scaling, and monitoring machine learning models in production environments. This role focuses on building reliable ML pipelines, optimizing model inference performance, and ensuring end-to-end lifecycle management of ML systems.

‍

• Build, deploy, and scale ML models using Docker and Kubernetes (EKS/AKS).

• Develop and manage CI/CD pipelines using GitHub Actions / Jenkins.

• Design and maintain low-latency, high-throughput REST/gRPC services for ML model serving.

• Implement model serving and inference using vLLM, Triton Inference Server, or TGI.

• Optimize inference performance by tuning batch sizes, managing GPU memory, and improving throughput.

• Implement logging of prompt/response pairs, monitor model performance, and detect model drift.

• Set up monitoring and observability using LangFuse, Helicone, or similar tools.

• Build and manage ML pipelines and experiment tracking using MLflow or Weights & Biases.

• Develop automated retraining pipelines and manage model versioning and registry.

• Build and maintain data pipelines for training data ingestion, PII handling, and versioning using DVC.

• Work with data storage systems like ClickHouse or similar columnar databases.

‍

• Familiarity with Hugging Face ecosystem.

• Experience with GPU driver and CUDA troubleshooting.

• Experience in cost optimization for cloud GPU workloads or on-prem infrastructure.

‍

• 4–6 years of experience in MLOps / ML Engineering roles.

• Strong programming skills in Python (mandatory) and working knowledge of Bash.

• Hands-on experience with Kubernetes, Docker, and CI/CD pipelines.

• Experience in building and scaling REST/gRPC APIs and services.

• Strong understanding of system design for high-performance, scalable systems.

• Experience with Git-based version control workflows.

• Hands-on experience with model serving tools (vLLM, Triton, TGI).

• Strong understanding of ML lifecycle, model monitoring, and observability.

• Experience with experiment tracking tools (MLflow or Weights & Biases).

• Basic data engineering knowledge including data pipelines and versioning.

• Strong problem-solving skills and ability to work in a fast-paced environment.

• Impactful Work: Build and scale ML systems that power intelligent, real-time communication platforms.

• Tremendous Growth Opportunities: Work on cutting-edge AI/ML technologies and advance your expertise in MLOps.

• Innovative Environment: Be part of a fast-paced, AI-driven ecosystem focused on experimentation and continuous improvement.

‍

Tanla is an equal opportunity employer. We champion diversity and are committed to creating an inclusive environment for all employees.