Ranking: 2607
Design technical architectures to integrate OpenAI, Azure OpenAI, GCP Vertex AI, and AWS Bedrock.
Define invocation patterns, security, authentication, observability, and governance for model consumption.
Design and implement MCP and A2A architectures to enable secure communication and orchestration between agents, services, and LLMs.
Design and develop end-to-end PoCs to validate integration products (Kong, Solo.io, Apigee, NGINX) and GenAI solutions.
Experiment with advanced capabilities such as:
Multi-provider routing
MCP extensions
A2A workflows
Basic RAG implementations
Model benchmarking and evaluation
Document technical findings to support product selection and industrialization decisions.
Perform hands-on implementation and delivery, configuring, deploying, and integrating selected technologies into corporate environments.
Advanced configuration of gateways, policies, plugins, extensions, security, tracing, and observability.
Integrate solutions with internal ecosystems: IAM, private networks, observability stacks, CI/CD, IaC, auditing, and compliance.
Build required technical artifacts such as scripts, modules, connectors, and pipelines.
Develop in Python to create connectors, automation tools, integration tests, internal SDKs, and GenAI experimentation utilities.
Automate infrastructure and deployments using Terraform and/or CloudFormation.
Build and maintain CI/CD pipelines using tools such as GitHub Actions, Azure DevOps, or Google Cloud Build.
Strong hands-on experience in DevOps and Infrastructure as Code.
Practical experience integrating LLM providers (OpenAI, Azure OpenAI, Vertex AI, Bedrock).
Experience configuring and extending API gateways (Kong, Solo.io, NGINX, Apigee or similar).
Solid knowledge of cloud-native architectures and security best practices.
Proficiency in Python for automation and backend tooling.
Experience with CI/CD pipelines and cloud infrastructure.
English level B2 (technical and professional communication).
Design technical architectures to integrate OpenAI, Azure OpenAI, GCP Vertex AI, and AWS Bedrock.
Define invocation patterns, security, authentication, observability, and governance for model consumption.
Design and implement MCP and A2A architectures to enable secure communication and orchestration between agents, services, and LLMs.
Design and develop end-to-end PoCs to validate integration products (Kong, Solo.io, Apigee, NGINX) and GenAI solutions.
Experiment with advanced capabilities such as:
Multi-provider routing
MCP extensions
A2A workflows
Basic RAG implementations
Model benchmarking and evaluation
Document technical findings to support product selection and industrialization decisions.
Perform hands-on implementation and delivery, configuring, deploying, and integrating selected technologies into corporate environments.
Advanced configuration of gateways, policies, plugins, extensions, security, tracing, and observability.
Integrate solutions with internal ecosystems: IAM, private networks, observability stacks, CI/CD, IaC, auditing, and compliance.
Build required technical artifacts such as scripts, modules, connectors, and pipelines.
Develop in Python to create connectors, automation tools, integration tests, internal SDKs, and GenAI experimentation utilities.
Automate infrastructure and deployments using Terraform and/or CloudFormation.
Build and maintain CI/CD pipelines using tools such as GitHub Actions, Azure DevOps, or Google Cloud Build.
Strong hands-on experience in DevOps and Infrastructure as Code.
Practical experience integrating LLM providers (OpenAI, Azure OpenAI, Vertex AI, Bedrock).
Experience configuring and extending API gateways (Kong, Solo.io, NGINX, Apigee or similar).
Solid knowledge of cloud-native architectures and security best practices.
Proficiency in Python for automation and backend tooling.
Experience with CI/CD pipelines and cloud infrastructure.
English level B2 (technical and professional communication).
