AI ML Ops Engineer

About Tarento: Tarento is a fast-growing technology consulting company headquartered in Stockholm, with a strong presence in India and clients across the globe. We specialize in digital transformation, product engineering, and enterprise solutions, working across diverse industries including retail, manufacturing, and healthcare.

Our teams combine Nordic values with Indian expertise to deliver innovative, scalable, and high-impact solutions. We're proud to be recognized as a Great Place to Work , a testament to our inclusive culture, strong leadership, and commitment to employee well-being and growth. At Tarento, you’ll be part of a collaborative environment where ideas are valued, learning is continuous, and careers are built on passion and purpose.

Designation: Senior Software Engineer – Analytics Location : Indore Educational Qualifications : B.E/B.Tech Exp : 3-5 Years Mode of work : Hybrid Role Overview We are seeking an AI/ML Ops Engineer to own the deployment, monitoring, and scaling of ML models and pipelines in production. You will build the infrastructure and automation that lets models move reliably from training to production and stay healthy once there.

What you'll do

Deploy and scale ASR, NMT and TTS models on GPU servers using Docker, Kubernetes and Triton Inference Server Build and maintain CI/CD pipelines that take models from training to production Monitor services for latency, throughput, errors and GPU utilization, and help debug production issues Help optimize inference performance for real-time use cases such as live transcription and voice agents Help manage GPU capacity across cloud and on-prem environments Must have 2+ years of hands-on Docker and Kubernetes experience CI/CD tooling (GitHub Actions, GitLab CI or Jenkins) Strong Python for automation and tooling Experience on any cloud platform (AWS, Azure or GCP) Has deployed at least one ML model to production with any serving framework (Triton, Torch.

Serve, FastAPI or similar) Comfortable with Linux and debugging services Good to have Triton Inference Server: model repositories and dynamic batching GPU infrastructure (NVIDIA drivers/CUDA, GPUs on Kubernetes) Prometheus and Grafana ONNX or TensorRT model conversion Serving speech or LLM models where latency matters gRPC or streaming services NVIDIA NVCF or NIM Helm or Terraform