Middle AI Engineer

Argentina, Argentina

Qinshift

Avenga - your information technology partner with more than 20 years of experience in entrepreneurship, leadership, and project delivery.

View all jobs at Qinshift

Apply now Apply later

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 UI design, managed services, product development, and software development.

This is your role

  • Design, develop, and implement GenAI-driven solutions using modern tools and best practices.
  • Build intelligent agents capable of retrieving, analyzing, and reasoning over both structured and unstructured data.
  • Collaborate with product and engineering teams to embed AI capabilities into existing ERP and scheduling systems.
  • Work on real-world use cases like inspection analysis, proposal generation, scheduling optimization, routing, diagnostics, onboarding, and NLP-based reporting.
  • Optimize LLM performance through effective prompt design, evaluation, and reduction of hallucinations.
  • Contribute to defining the technical direction and best practices for scalable GenAI integration.
  • Stay up to date with the latest in open-source LLMs, vector DBs, and multi-agent systems.

This is you

  • 3+ years of experience in AI engineering, with hands-on involvement in building and deploying LLM-powered applications.
  • Strong proficiency in Python, especially in the context of machine learning and generative AI workflows.
  • Experience working directly with Large Language Models (LLMs) such as OpenAI, Claude, Gemini, Llama, Mistral, etc.
  • Familiarity with GenAI abstraction frameworks like LangChain or Vercel AI SDK.
  • Solid understanding of Retrieval-Augmented Generation (RAG) techniques, including document ingestion, chunking strategies, embeddings, and semantic search.
  • Experience working with vector databases (e.g., Pinecone, Qdrant, FAISS, ChromaDB).
  • Practical knowledge of prompt engineering and tuning techniques to improve LLM responses.
  • Experience developing within AWS and/or Azure cloud environments for AI workloads.
  • Awareness of LLM evaluation methods and metrics, including red teaming, accuracy checks, and hallucination mitigation.
  • Understanding of agentic workflows — including multi-step processing, feedback loops, multi-agent systems, and memory. 

Nice-to-have skills:

  • Background in machine learning or data science.
  • Experience implementing AI features within SaaS or ERP products.
  • Familiarity with real-world applications in industries like fire & safety, aviation, pool service, or waste management.

What awaits you at Avenga?

An opportunity to work on meaningful, cutting-edge GenAI use cases that have real-world impact.

Collaborative and inclusive culture where innovation and experimentation are encouraged.

Access to global expertise and continuous learning in the fast-evolving AI space.

Flexible working model and supportive environment for career growth.


Apply now Apply later

* Salary range is an estimate based on our AI, ML, Data Science Salary Index 💰

Job stats:  1  1  0

Tags: AWS Azure Claude CX Engineering FAISS Gemini Generative AI LangChain LLaMA LLMs Machine Learning NLP OpenAI Open Source Pinecone Prompt engineering Python RAG Unstructured data UX

Perks/benefits: Career development Flex hours

Region: South America
Country: Argentina

More jobs like this