AI Delivery Lead: RAG, LLMs & MLOps Architect

Visa Hunt; Argentina; Presencial; ARS 181.190.000 - 271.784.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Lunches at headquarters

MacBook and accessories provided

Snacks and beverages

Descripción de la vacante

Blend360, LATAM team, is seeking an AI Engineer Manager to design, build, and deploy production-ready AI systems across the full stack, including RAG pipelines and evaluation design. You will mentor engineers, communicate with stakeholders, and help clients make pragmatic AI choices.

The role is remote for LATAM, full-time, focusing on end-to-end AI delivery, governance, and continuous improvement in a fast-paced environment.

Formación

• 6+ years of experience building and deploying AI/ML or data-driven solutions in production environments.
• Strong expertise in Python and solid Git practices.
• Hands-on experience with LLM-powered solutions, RAG systems, and modern GenAI development patterns.
• Practical experience with RAG components, including chunking, embeddings, retrieval, reranking, and evaluation.
• Strong understanding of prompt engineering techniques, including structured outputs, few-shot prompting, instruction design, and tool/agent prompts.
• Proven experience designing evaluation strategies for AI systems, including metrics, dataset curation, structured experimentation, and quality gates.
• Experience with MLOps/LLMOps practices and tools such as MLflow, Weights & Biases, or similar platforms.
• Solid cloud experience with AWS, Azure, or GCP. Azure experience is preferred.
• Experience with containerization, orchestration, scalable inference, APIs, and microservices.
• Understanding of event-driven architectures and production-grade engineering practices.
• Ability to communicate clearly with engineering teams, senior stakeholders, and clients.
• A pragmatic approach to AI delivery, balancing innovation, reliability, cost, latency, and business value.

Responsabilidades

• Leading AI project delivery end to end with clear governance and reliable execution.
• Designing and building robust RAG systems, agentic frameworks, and LLM-powered solutions for production environments.
• Applying advanced prompt engineering techniques, including instruction design, few-shot prompting, structured outputs, and tool/agent prompts.
• Leading feasibility assessments to determine the right technical approach (prompting, RAG, fine-tuning, classical ML, hybrid).
• Designing evaluation frameworks for AI systems, including LLM-as-a-judge, custom metrics, recall@k, precision@k, and go/no-go gates.
• Running structured experiments across prompts, retrievers, chunking strategies, embeddings, reranking, and models.
• Identifying and categorizing model failures such as hallucinations and retrieval misses.
• Building scalable inference infrastructure and CI/CD pipelines for AI/ML models.
• Automating the MLOps/LLMOps lifecycle including tracking, deployment, monitoring, retraining, and continuous improvement.
• Designing APIs, microservices, and orchestration layers optimized for latency, cost, reliability, and scalability.
• Mentoring junior engineers and contributing to proposals and new business initiatives.

Conocimientos

AI/ML production

Python

LLM-powered solutions

RAG systems

Prompt engineering

MLOps/LLMOps

Cloud platforms

Docker/Kubernetes

APIs & microservices

Stakeholder communication

Team leadership

Herramientas

MLflow

Weights & Biases

Databricks MLOps

Terraform

Docker

Kubernetes

Descripción del empleo

Blend360, LATAM team, is seeking an AI Engineer Manager to design, build, and deploy production-ready AI systems across the full stack, including RAG pipelines and evaluation design. You will mentor engineers, communicate with stakeholders, and help clients make pragmatic AI choices.

The role is remote for LATAM, full-time, focusing on end-to-end AI delivery, governance, and continuous improvement in a fast-paced environment.