GenAI-First Python Engineer – Backend & AI Pipelines

Avenga; Buenos Aires; Híbrido; ARS 1.200.000 - 1.800.000; Jornada completa

Descripción de la vacante

Avenga is seeking a Senior Python Engineer with AI expertise to join a GenAI-first team focused on scalable, secure Generative AI solutions. You will work on backend services and integrate LLM capabilities across platforms, emphasizing production-ready architectures.

Ideal candidates have 4–6 years as backend engineers with 1–2 years in GenAI, strong cloud-native skills, and familiarity with LangChain, FastAPI, and AI security practices.

Formación

• 4–6 years of backend/software engineering experience.
• 1–2 years hands-on experience with GenAI technologies (LLMs, RAG, LangChain).
• Strong foundation in software engineering principles and cloud-native development.

Responsabilidades

• Design, develop, and maintain Python-based backend services integrating Generative AI.
• Build robust, scalable, and secure AI applications aligned with business requirements.
• Develop and integrate LLM capabilities into products and platforms.
• Implement RAG architectures using vector databases and semantic search solutions.
• Create and maintain AI pipelines, APIs, and agent-based frameworks.
• Optimize prompts, embeddings, and token usage to balance cost and performance.
• Ensure observability, monitoring, and validation of AI systems in production.
• Collaborate with product, engineering, and business teams to deliver AI-powered solutions.
• Document technical solutions to support onboarding, scalability, and maintainability.

Conocimientos

Python

Backend engineering

GenAI

LangChain

LangGraph

FastAPI

LLMs

Cloud-native

Docker

Kubernetes

CI/CD

Terraform

RAG

Prompt engineering

Embeddings

Herramientas

LangChain

LangGraph

FastAPI

OpenAI GPT

Claude

Gemini

Azure

AWS

Docker

Kubernetes

CI/CD

Terraform

Descripción del empleo

Avenga is seeking a Senior Python Engineer with AI expertise to join a GenAI-first team focused on scalable, secure Generative AI solutions. You will work on backend services and integrate LLM capabilities across platforms, emphasizing production-ready architectures.

Ideal candidates have 4–6 years as backend engineers with 1–2 years in GenAI, strong cloud-native skills, and familiarity with LangChain, FastAPI, and AI security practices.