Role Overview :
We are hiring a GenAI Platform Engineer to build and manage secure, scalable Generative AI infrastructure.
This role focuses on configuring Enterprise GPT platforms, managing identity integrations (SSO), connecting internal data sources, and enabling RAG (Retrieval-Augmented Generation) use cases.
Key Responsibilities :
- Set up and secure Enterprise GPT instances
- Integrate with SSO and manage access controls
- Build APIs and connectors to internal data sources
- Build APIs for RAG and Agentic AI solutions
- Ensure data privacy, security, and compliance
- Collaborate with data, security, and product teams
- Deploying Applications, Application Servers, Virtual Machines, Databases, Serverless
Components, and other infrastructure services both on Cloud and On-Prem
Requirements : Required Skills :
Experience working with Linux / UNIX systems, Docker & Kubernetes, Cloud (such as Azure, AWS)Python and / or Node.jsAPI development and integrationSSO and identity management (OAuth, SAML, etc.)Familiarity with Databricks and data workflowsDatabase experience, including knowledge of SQL and NoSQL, and related data stores such as PostgresData security and privacy best practicesGood To Have :
RAG and GenAI implementation experienceExperience with vector DBs (e.g., FAISS, Pinecone)Knowledge of LangChain, LlamaIndex, or similar toolsAwareness of networking and internet protocols, including TCP / IP, DNS, SMTP, HTTP, and distributed networks and security conceptsMandatory Skills : Python, Docker, Kubernetes, Databricks, Azure, AWS, SQL
(ref : hirist.tech)