AI Engineer Buenos Aires ·

Avenga; Buenos Aires; Híbrido; ARS 1.500.000 - 2.100.000; Jornada completa

Descripción de la vacante

Avenga is seeking a Senior AI Engineer to join our Tech Solutions team. You will help shape AI strategy, build reusable components, and drive adoption across multiple products and engineering teams.

The role combines hands-on software engineering with architectural ownership, enabling you to research AI tech and deliver secure, observable, scalable solutions. You will work closely with stakeholders and contribute to architectural decisions and best practices.

Formación

• Senior backend experience with scalable systems.
• Strong Node.js and JavaScript/TypeScript proficiency.
• Hands-on AWS, serverless architectures, and distributed systems.
• Experience designing APIs and reusable components for multiple products.
• Strong understanding of testing, security, observability, and CI/CD practices.
• Experience contributing to software architecture and engineering decisions.
• Hands-on experience with Large Language Models (LLMs) and Generative AI.
• Ability to translate business and technical requirements into generic, scalable solutions.
• Ability to research emerging technologies and convert concepts into production-ready tools.
• Self-driven with ownership and strong collaboration and documentation skills.

Responsabilidades

• Design and develop reusable components, libraries, APIs, plugins, and tools enabling AI adoption across teams.
• Integrate AI capabilities into internal development frameworks for easy adoption.
• Define reference architectures, patterns, standards, and best practices for Generative AI solutions.
• Design and implement integrations with LLMs and AI services, mainly within AWS.
• Develop production-ready solutions using Node.js, TypeScript, serverless tech, and Serverless Framework.
• Explore AI capabilities like structured generation, tool calling, agents, RAG, MCP, embeddings, and semantic search.
• Define testing and evaluation mechanisms for quality, security, latency, reliability and cost.
• Implement observability for model usage, prompts, tokens, responses, errors and timings.
• Establish technical controls to protect sensitive information and promote secure AI usage.
• Build PoCs for emerging tech and evolve into scalable production solutions.
• Create comprehensive technical docs, examples and adoption guidelines.

Conocimientos

Senior backend

Node.js

JavaScript

TypeScript

AWS

Serverless

APIs design

Software architecture

CI/CD

LLMs / Generative AI

Research & prototyping

Ownership & autonomy

Documentation & communication

Cross-team collaboration

Herramientas

Serverless Framework

AWS Lambda

API Gateway

Step Functions

DynamoDB

Vector databases

MCP

Observability tools

Descripción del empleo

This is us

At Avenga, we believe that human creativity empowers technology that matters. Operating globally, our 6000+ specialists provide a full spectrum of services, including business and tech advisory, enterprise solutions, CX, UX and Ul design, managed services, product development, and software development.

This is the job

We are looking for a Senior AI Engineer to join a Tech Solutions team responsible for building reusable technology components and solutions, defining architectures, and promoting engineering best practices across development teams.

You will be the first AI Enablement specialist within the team, playing a key role in defining the strategy, capabilities, and engineering standards required to integrate Artificial Intelligence into the organization's development ecosystem.

This role combines hands-on software engineering with architectural ownership and technology exploration. You will research emerging AI technologies and transform them into production-ready, secure, observable, scalable, and easy-to-adopt solutions that can be reused across multiple products and engineering teams.

This is you

• Senior-level experience in backend software development.
• Strong expertise in Node.js and solid experience with JavaScript and/or TypeScript.
• Hands-on experience with AWS, serverless architectures, and distributed systems.
• Experience designing and developing APIs, libraries, frameworks, plugins, or other reusable software components.
• Strong understanding of software design principles and engineering best practices, including testing, security, observability, and CI/CD.
• Experience contributing to software architecture, technical design, and engineering decision-making.
• Hands-on experience developing or integrating solutions based on Large Language Models (LLMs) and Generative AI.
• Ability to translate specific business and technical requirements into generic, scalable, and reusable solutions.
• Ability to research emerging technologies, evaluate alternatives, and transform concepts and proof-of-concepts into production-ready solutions.
• Self-driven mindset with a high degree of ownership and autonomy.
• Strong communication, technical documentation, and cross-team collaboration skills.

Nice-to-have skills

• Experience with Amazon Bedrock or other Generative AI platforms.
• Experience with the Serverless Framework and plugin development.
• Hands-on knowledge of RAG, AI agents, tool calling, Model Context Protocol (MCP), structured generation, embeddings, and semantic search.
• Experience with AWS services such as Lambda, API Gateway, Step Functions, EventBridge, SQS, SNS, and DynamoDB.
• Knowledge of vector databases and semantic search technologies.
• Experience implementing evaluation frameworks, guardrails, observability, and operational practices for LLM-based applications.
• Experience building internal development platforms, frameworks, or developer tools.

This is your role

• Design and develop reusable components, libraries, APIs, plugins, and tools that enable AI adoption across products and engineering teams.
• Integrate AI capabilities into the organization's internal development framework and make them easy for other engineering teams to adopt.
• Define reference architectures, technical patterns, standards, and best practices for Generative AI-based solutions.
• Design and implement integrations with Large Language Models and AI services, primarily within the AWS ecosystem.
• Develop production-ready solutions using Node.js, TypeScript, serverless architectures, and the Serverless Framework.
• Explore and implement AI capabilities such as structured generation, tool calling, agents, RAG, MCP, embeddings, and semantic search.
• Define testing and evaluation mechanisms to measure the quality, security, latency, reliability, and cost of AI-powered solutions.
• Implement observability for model usage, prompts, tokens, responses, errors, execution times, and other relevant operational metrics.
• Establish technical controls and engineering practices to protect sensitive information and promote secure and responsible AI usage.
• Build proof-of-concepts for emerging technologies and evolve successful approaches into scalable, maintainable, production-ready solutions.
• Create comprehensive technical documentation, implementation examples, and adoption guidelines for engineering teams.
• Support development teams in adopting reusable AI components, architectures, and engineering best practices.
• Participate in architecture reviews and contribute to technical decision-making across the organization.
• Share knowledge and promote AI engineering best practices within the broader engineering community.

What awaits you at Avenga?

At Avenga, everyone matters. We provide equal opportunities in recruitment, career development, and leadership, regardless of race, ethnicity, gender identity, sexual orientation, disability, age, religion, or any other characteristic. We are committed to fostering a work environment where our diverse community of employees, candidates, and business partners actively shapes our growth. By bringing together people from different backgrounds and experiences, we build a workplace where everyone feels free to be themselves while honoring the boundaries of others