MLOps Engineer
Location : Hyderabad / Bangalore, India
Type : Full-Time | Immediate Joining Preferred
CTC : Competitive
About YAL.ai
YAL.ai (Your Alternative Life) is reimagining the way people connect, communicate, and discover in a digital-first world. Our platform brings together instant messaging, dynamic communities, and real-time voice and video, all powered by advanced artificial intelligence. From multilingual speech intelligence and speech-to-speech systems to fraud detection and personalized recommendations, every layer of YAL.ai is designed with security, privacy, and intelligence at its core.
Built on a Zero Trust Architecture, YAL.ai ensures that every interaction is verified and safeguarded. Unlike conventional platforms, we place privacy and user trust at the forefront while still pushing the boundaries of what AI can deliver in real time. With our vision, “Where AI Meets Integrity,” we are building an ecosystem that is fast, safe, multilingual, and personalized creating meaningful and impactful connections for millions of users worldwide.
Role Overview
We are seeking an MLOps Engineer to design, automate, and scale the machine learning infrastructure that powers YAL.ai’s core AI systems. This role sits at the intersection of research and production, ensuring that models built by our AI teams seamlessly transition into robust, secure, and highly available deployments across cloud and edge environments.
Key Responsibilities
End-to-End ML Deployment
- Design, build & maintain production-grade pipelines for training, deploying, and monitoring ML models.
- Deploy models for speech-to-text, text-to-speech, NLP, and LLM-powered conversational systems in real-time.
- Optimize inference latency for low-latency streaming systems .
Real-Time & Scalable Infrastructure
Build and maintain real-time ML services capable of handling millions of daily requests.Implement scalable solutions using Kubernetes, Docker, and cloud-native architectures (AWS, GCP, or Azure).Integrate models into messaging / chat applications and other conversational platforms.Automation & CI / CD
Develop CI / CD pipelines for continuous training (CT) and continuous deployment (CD) of ML models.Automate model versioning, packaging, and rollout with tools like MLflow, Kubeflow, Sagemaker , or similar.Monitoring & Observability
Create real-time dashboards using Prometheus, Grafana, or Datadog for monitoring model health and performance.Implement data drift detection, anomaly monitoring , and automated retraining triggers.Collaboration & Best Practices
Work closely with data scientists to productionize research models into stable APIs and services.Define best practices for ML pipelines , model governance, and experiment tracking.Ensure security and compliance , including safe handling of sensitive data like PII and voice data.Technical Skills
Technical Expertise :
Strong experience with Python and ML deployment frameworks.Proficiency with container orchestration : Docker, Kubernetes.Familiarity with streaming systems like Kafka, Redis Streams, or Flink for real-time data.Hands-on experience deploying deep learning models (PyTorch, TensorFlow).Experience with GPU / TPU optimization for real-time inference.MLOps Tools :
MLflow, Kubeflow, Airflow, or equivalent pipeline orchestration tools.Model serving frameworks like TorchServe, TensorFlow Serving, Triton Inference Server , or BentoML.Cloud ML services (AWS Sagemaker, GCP Vertex AI, Azure ML).Speech & NLP Focus :
Knowledge of speech processing models (ASR, TTS, speaker identification).Experience with large language models (LLMs) and conversational AI architectures .DevOps & Monitoring :
CI / CD pipelines with GitHub Actions, Jenkins, or GitLab CI.Observability stack : Prometheus, Grafana, Datadog, ELK.Soft Skills :
Strong problem-solving and debugging skills.Excellent communication skills for cross-functional collaboration.Passion for scalable AI systems and real-time performance.Qualifications
Bachelor’s or Master’s in Computer Science, Data Engineering, or a related field.Proven track record of building ML pipelines and deploying models into production.Experience managing large-scale ML infrastructure with GPUs / TPUs.Bonus If You Have
Knowledge of on-device / edge AI deployment (TFLite, CoreML, quantization workflows).Experience with serverless ML serving (Vertex AI, AWS SageMaker, Lambda).Contributions to open-source MLOps tools or projects.Experience with multi-model orchestration (fraud detection + speech + recommendations).How to Apply
Apply directly via LinkedIn or DM us orSend your CV + infra / work samples (GitHub, architecture diagrams, repos) to with Subject : (MLOps Engineer | Your Name)