Senior Specialist - AI Engineering

Senior AI Platform Engineer

Role Overview

We are seeking a Senior AI Platform Engineer with overall 7 to 10 years of experience to design build and operate a secure scalable enterprise AI platform on Microsoft Azure primarily hosted on Azure Kubernetes Service AKS

The role requires a strong platform engineering mindset combining AI engineering cloudnative engineering DevSecOps LLMOps security automation observability and operational excellence The engineer will create reusable platform capabilities that enable teams to build and productionize generative AI RAG and agentic AI solutions efficiently

Key Responsibilities

Design build and operate scalable AI platform capabilities on Azure and AKS

Engineer capabilities for LLM applications RAG solutions AI agents multiagent workflows AI gateways guardrails and model evaluation

Develop reusable platform services APIs deployment templates and reference implementations

Build agent harness capabilities covering orchestration tool integration memory context management state management policy enforcement tracing and exception handling

Enable secure integration with enterprise tools and data sources using Model Context Protocol MCP APIs connectors and eventdriven patterns

Build reusable RAG pipelines covering document ingestion chunking embeddings vector indexing retrieval reranking grounding and citations

Implement vector database and enterprise search capabilities using technologies such as Azure AI Search PostgreSQL with pgvector or equivalent platforms

Implement centralized AI guardrails for prompt injection unsafe content sensitivedata exposure inappropriate tool execution and unauthorized access

Establish CICD and Infrastructure as Code practices using GitHub GitHub Actions Terraform and container technologies

Embed security testing container scanning dependency scanning policy validation AI evaluation and guardrail testing into delivery pipelines

Implement endtoend observability for infrastructure applications LLM calls token consumption RAG pipelines agent workflows security events and costs

Apply SRE practices covering availability performance capacity incident response resilience disaster recovery and automated remediation

Provide selfservice onboarding golden paths sample repositories documentation and operational runbooks for engineering teams

Collaborate with architects AI engineers developers security risk data and operations teams to establish enterprise AI platform standards

Primary Skills

Microsoft Azure and Azure Kubernetes Service

Kubernetes Docker and container orchestration

Azure OpenAI and Microsoft Foundry

Large Language Models and generative AI

Agentic AI and multiagent systems

Agent harness and orchestration engineering

Model Context Protocol and tool integration

RetrievalAugmented Generation

Embeddings vector search and vector databases

Azure AI Search PostgreSQL and pgvector

AI gateways model gateways and API Management

AI guardrails content safety and responsible AI

Prompt model RAG and agent evaluation

LLMOps MLOps and AI observability

GitHub GitHub Actions and DevSecOps

Terraform Bicep and Infrastructure as Code

Entra ID managed identity RBAC Key Vault and private networking

Azure Monitor Application Insights OpenTelemetry Prometheus and Grafana

Python and any other programming language like Java C

LangChain LangGraph Semantic Kernel AutoGen or equivalent frameworks

Required Qualifications

Strong experience in building an enterprise AI platform cloud engineering DevOps SRE or distributed systems

Practical experience with LLMs RAG embeddings vector databases AI agents MCP guardrails and AI evaluation

Experience with Azure AI Search Azure API Management Azure Container Registry Key Vault and Azure monitoring services

Experience with LangChain LangGraph Semantic Kernel MCP servers agent registries tool catalogs or model gateways

Experience implementing multitenant AI platforms with workload identity network data and cost isolation

Familiarity with AI governance privacy model risk management threat modeling and regulatory controls

Handson experience designing and operating production workloads on Azure and AKS

Strong knowledge of Kubernetes networking security scaling identity observability and workload isolation

Experience building automated delivery pipelines using GitHub Actions and Infrastructure as Code

Strong understanding of APIs microservices eventdriven integration authentication authorization and secure software development

Experience operationalizing production platforms with defined availability performance security and support requirements

Proficiency in at least one modern programming language

Strong troubleshooting documentation collab