AI Platform Engineer

Job Summary Experience : 5+ Years We are seeking an experienced AI Platform Engineer to design, build, and maintain scalable platforms supporting machine learning, generative AI, and large language model applications. This role will focus on creating reliable infrastructure, deployment pipelines, model-serving capabilities, monitoring systems, and governance controls that enable AI teams to move efficiently from experimentation to production. The ideal candidate will have strong experience in cloud infrastructure, Kubernetes, MLOps, CI/CD automation, Python, and production deployment of machine learning or generative AI workloads. Key Responsibilities Design and develop scalable AI and machine learning platform architecture. Build infrastructure for training, evaluating, deploying, and monitoring ML and generative AI models. Develop standardized CI/CD pipelines for model and AI application deployment. Deploy and manage AI workloads using Docker, Kubernetes, and cloud-native services. Build and maintain model-serving infrastructure for real-time and batch inference. Support the deployment of large language models, embedding models, and retrieval-augmented generation applications. Implement model registries, experiment tracking, feature stores, prompt management, and evaluation frameworks. Develop APIs and reusable platform services for data scientists and AI application developers. Optimize inference performance, GPU utilization, scalability, availability, and operating costs. Establish monitoring for model performance, latency, throughput, drift, failures, and infrastructure health. Implement platform security, role-based access controls, secrets management, audit logging, and data protection. Integrate vector databases and enterprise data sources with generative AI applications. Automate infrastructure provisioning using Terraform or similar Infrastructure-as-Code tools. Partner with data science, engineering, DevOps, cloud, security, and governance teams. Define platform standards, deployment patterns, technical documentation, and operational procedures. Troubleshoot production issues and improve platform reliability through automation and observability. Required Qualifications Bachelor’s or Master’s degree in Computer Science, Engineering, Data Science, or a related technical discipline. 5+ years of experience in software engineering, cloud engineering, DevOps, platform engineering, or MLOps. Hands-on experience building or supporting production AI/ML platforms. Strong programming experience with Python. Experience with at least one major cloud platform: AWS, Azure, or Google Cloud. Strong experience with Docker and Kubernetes. Experience with CI/CD tools such as GitHub Actions, GitLab CI, Jenkins, or Azure DevOps. Experience with Infrastructure as Code using Terraform, CloudFormation, or Pulumi. Knowledge of machine learning workflows, model deployment, model versioning, and inference patterns. Experience with MLflow, Kubeflow, SageMaker, Azure Machine Learning, Vertex AI, or comparable platforms. Understanding of REST APIs, microservices, distributed systems, and event-driven architecture. Experience with observability tools such as Prometheus, Grafana, OpenTelemetry, Datadog, or CloudWatch. Strong understanding of cloud security, IAM, networking, encryption, and secrets management. Preferred Qualifications Experience deploying generative AI and large language model applications. Knowledge of RAG architecture, prompt engineering, embeddings, and vector search. Experience with frameworks such as LangChain, LlamaIndex, Semantic Kernel, or Hugging Face. Familiarity with vector databases such as Pinecone, Weaviate, Milvus, Qdrant, OpenSearch, or PostgreSQL with pgvector. Experience serving models using NVIDIA Triton, KServe, Ray Serve, vLLM, TorchServe, or TensorFlow Serving. Knowledge of GPU infrastructure and distributed training or inference. Experience implementing AI evaluation, guardrails, responsible AI, and model governance controls. Familiarity with data platforms such as Snowflake, Databricks, Apache Spark, or Kafka. Experience optimizing AI infrastructure for performance and cost. Core Technical Skills Programming: Python, SQL, Bash Cloud: AWS, Azure, or Google Cloud Containers: Docker, Kubernetes, Helm MLOps: MLflow, Kubeflow, SageMaker, Azure ML, or Vertex AI Infrastructure: Terraform, CloudFormation, or Pulumi CI/CD: GitHub Actions, Jenkins, GitLab CI, or Azure DevOps Generative AI: LLMs, RAG, embeddings, prompt management, model evaluation Monitoring: Prometheus, Grafana, OpenTelemetry, Datadog, or CloudWatch Databases: PostgreSQL, NoSQL databases, and vector databases Success in This Role The successful candidate will build a secure, reliable, and developer-friendly AI platform that reduces the time required to move AI solutions from development into production while maintaining strong standards for scalability, observability, governance, and cost efficiency. Show more Show less