AI Engineer

Job title: AI Engineer

About the Role You are a hands-on AI Engineer who builds and ships intelligent, user-centric solutions. With expertise in LLMs, data pipelines, and modern engineering practices, you design and deploy scalable AI-powered applications across the full AI stack—from data and prompt design to model tuning, RAG, and agentic workflows. You care deeply about AI-driven UX and creating intuitive, reliable experiences while managing context, latency, and evaluation. You’ll collaborate with a global team to deliver cutting-edge solutions across conversational AI, automation, and agent-based systems.

What You'll Do

• Build AI-powered solutions for client projects, from discovery through production
• Integrate AI models (OpenAI, open-source LLMs, etc.) into production systems and APIs
• Develop and optimize prompts, retrieval systems (RAG), and agent-based workflows
• Implement guardrails, observability, and monitoring for AI systems
• Optimize performance, latency, and cost of AI applications
• Rapidly prototype solutions to validate ideas and demonstrate value to clients
• Document approaches, experiments, and system architecture clearly
• Work cooperatively with Modus project and account managers, designers, engineers, and other team members, as required
• Report progress/updates and/or communicate with other team members, project leads, and our clients, as required
• Other duties related to the position that may arise from time to time and as may be assigned

What We're Looking For

• 5+ years of experience in software engineering, machine learning, or related fields
• Strong programming skills in JavaScript and TypeScript for integration
• Hands-on experience with LLMs and modern AI tools and frameworks (e.g., OpenAI APIs, LangChain, vector databases)
• Understanding of RAG architectures, embeddings, and semantic search
• Experience integrating AI into full-stack applications (APIs, frontends, backend services)
• Familiarity with cloud platforms (AWS preferred)
• Strong communication skills with the ability to explain AI concepts to non-technical stakeholders and clients
• You’re located in Buenos Aires and are willing to work from our office at least 2 times a month (hybrid schedule)

Nice to Have

• Familiarity with LLM observability tools like Langfuse
• Experience with evaluation frameworks and prompt testing methodologies
• Experience building AI agents or automation workflows
• Understanding of data pipelines for AI native formats

Compensation & Benefits

• Benefits: For a complete list of employee benefits, refer to your local Employee or Contractor Handbook, as appropriate
• Salary: Not disclosed in the posting