Senior Generative Artificial Intelligence and Autonomous Systems Engineer for Agent Development, Product Integration and API Architecture

March 13, 2026

No location

RemotoJOB

Apply
Descripción

Job Description

Job Description
Looking for a professional to lead the development of secure and autonomous artificial intelligence systems, integrating advanced technology and innovative solutions to solve complex, high-value problems. The position requires experience in generative AI systems, collaboration between product and engineering teams, and development of scalable and secure APIs.
Responsibilities:
Lead the development of secure and autonomous AI systems:
design intelligent agent-based tools, leveraging solutions such as Claude Code, MCP, A2A, Gemini CLI and the OpenAI Agent SDK, using knowledge graph concepts to solve complex problems.
Develop A2A systems:
create frameworks that allow LLMs to collaborate internally and externally, expanding the reach of generative AI systems with 3E technology.
Integrate product and engineering:
Collaborate with product, engineering, and customer teams to incorporate AI into tools that improve usability, decision-making, and automation.
Create seamless API integrations:
develop scalable and secure APIs that connect AI models with web applications, internal systems and external platforms, integrating them with MCP for use in agents.
Contribute to responsible AI practices:
keep up to date with advances in AI and help define responsible development standards, alignment strategies and security protocols.
Requirements:
Experience developing and deploying production-level AI systems as a software engineer, machine learning engineer, or in a similar role.
Hands-on experience with LLM, Generative AI, and agent frameworks such as MCP, A2A, and the OpenAI Agent SDK.
Ability to configure AI infrastructure, including production-grade model inference services, MLOps pipelines, and shared services.
Knowledge of AI security practices, alignment, and ethical development.
Experience with agent orchestration frameworks such as Claude Subagents, AutoGen or CrewAI.
Experience in prompt engineering, context engineering, RAG pipelines and optimization.
Experience using and deploying open source LLMs in production such as variants of Qwen, DeepSeek, Llama, Mistral and Gemma.
Familiarity with cloud-based AI tools (e.g. AWS Bedrock, GCP Vertex AI, Azure ML).
Experience integrating AI capabilities into web applications, desktop applications and legacy APIs.

Salary to receive
To agree