Responsibilities

- Integrate Generative AI models, including LLMs, with external APIs, tools, and databases using secure and efficient orchestration patterns.

- Design, develop, and deploy AI workflows and Agentic AI solutions, enabling the seamless orchestration of intelligent agents to plan and perform tasks while leveraging autonomous and/or human-in-the-loop paradigms.

- Implement and optimize multi-agent systems, leveraging standards and protocols such as Model Context Protocol (MCP) and emerging frameworks for agent interoperability.

- Develop evaluation frameworks, metrics, and checkpoints for agent autonomy, performance, and safety, ensuring compliance with moderation, security, and ethical standards.

- Ensure robust AI agent operations by applying observability, monitoring, and MLOps best practices, facilitating reliable deployment pipelines and continuous performance optimization.

- Collaborate closely with data experts, orchestrating AI model selection, tuning, and performance validation to meet specific agent-based application needs.

- Communicate complex AI concepts, systems, and decisions effectively to technical and non-technical stakeholders, promoting transparency and trust in AI delivery

Requirements

- Proven experience designing and deploying AI architectures, with expertise in Generative AI, NLP, LLM integration, and software engineering.

- Strong background in building software platforms (Python/Django, Java/Spring, TypeScript/Express, etc.) capable of API integration and orchestration.

- Strong understanding of the trade-offs between various generative AI models and the ability to choose the right model for specific use cases.

- Hands-on experience with function-calling and tools integration into LLM models, leveraging frameworks such as Model Context Protocol (MCP).

- Expertise in data embeddings, vector databases, and chunking strategies,



understanding the trade-off between different options, and leveraging it to optimize data ingestion and application performance.

- Experience using CI/CD tools (GitHub Actions, Jenkins, AWS CodeDeploy, Azure Pipelines) to streamline development and deployment workflows.

- Hands-on experience deploying software on leading cloud platforms and utilizing AI tools like AWS Bedrock and Azure AI Services.

- Experience leveraging evaluation frameworks (e.g., RAGAS, OpenAI Eval) and tools (e.g., DeepEval, LangSmith, Braintrust) to assess business and performance metrics of AI solutions.

- Understanding of performance optimization, including the use of observability platforms, event tracking, and performance validation.

- Practical knowledge of deploying AI solutions using cloud platforms like AWS, Azure, or GCP, utilizing services such as AWS Bedrock or Azure AI Services.

- Excellent skills in prompt and context engineering, ensuring the usage of the right techniques to meet diverse project requirements.

- Ability to communicate complex AI solutions and concepts effectively to technical and non-technical stakeholders.

Benefits

Benefits:

- Private health insurance for the family group (spouse and children).

- Versátil working hours.

- Hybrid work model (our offices are always open!).

- 15 business days of vacation.

- Lazy Days (days off without justification).

- Performance bonus.

- English classes during working hours.

- Access to learning platforms (Udemy, Platzi, and Crehana).

- Discounts on a wide variety of products, stores, and services.

- Welcome kit.

- Work tools (Mac, adapter, headphones, monitor).

- Cultural activities: Friday barbecues, soccer, game nights/afternoons, and more.

- Special gifts for occasions: birthdays, anniversaries, etc.

- Internal training: GM2 Talks.

- Offisnack (discounts on purchases).

- Knowledge Hubs aligned to business strategy

📌 AI Engineer (Buenos Aires)
🏢 GM2
📍 Buenos Aires