Platform Engineer
First seen by Alion on Sep 15, 2026.
Job Description :
What You'll Do :
- Deploy, scale, and operate ML and Generative AI systems in cloud-based production environments (Azure preferred).
- Build and manage enterprise-grade RAG applications using embeddings, vector search, and retrieval pipelines.
- Implement and operationalise agentic AI workflows with tool use, leveraging frameworks such as Lang Chain and Lang Graph.
- Develop reusable infrastructure and orchestration for GenAI systems using Model Context Protocol (MCP) and AI Development Kit (ADK).
- Design and implement model and agent serving architectures, including APIs, batch inference, and real-time workflows.
- Establish best practices for observability, monitoring, evaluation, and governance of GenAI pipelines in production.
- Integrate AI solutions into business workflows in collaboration with data engineering, application teams, and stakeholders.
- Drive adoption of MLOps / LLM Ops practices, including CI/CD automation, versioning, testing, and lifecycle management.
- Ensure security, compliance, reliability, and cost optimisation of AI services deployed at scale.
What You Know :
- 5 - 9 years of experience in ML Engineering, AI Platform Engineering, or Cloud AI Deployment roles.
- Strong proficiency in Python, with experience building production-ready AI/ML services and workflows.
- Proven experience deploying and supporting GenAI applications in real-world enterprise environments.
- Experience with orchestration frameworks, including but not limited to Lang Chain, Lang Graph, and Lang Smith.
- Strong knowledge of model serving inference pipelines, monitoring, and observability for AI systems.
- Experience working with cloud AI ecosystems (Azure AI, Azure ML, Databricks preferred).
- Familiarity with containerization and deployment tools (Docker, Kubernetes, REST) and Role & responsibilities.
Skills
Python, LangChain, Azure, Databricks, RESTful, Machine Learning, Generative AI, Workflows, Agentic AI