Senior AI Engineer

Please watch this 2-minute video first:

https://www.loom.com/share/17ce36af3f2a4336bbd2fb22e21917c1

Self Inspection | Remote — Latin America | 5+ years experience

About the Role

Self Inspection is transforming vehicle inspections with AI-powered computer vision and intelligent automation — turning a smartphone camera into an inspection tool used by some of the largest automotive companies in North America.

You'll design, build, and deploy the AI-powered products and systems that enhance inspection workflows, automate decision-making, and improve customer experiences: LLM applications, agents, RAG systems, and multimodal AI that combines text, images, documents, structured data, and computer vision outputs. You'll work closely with Computer Vision engineers, backend engineers, product, and leadership to ship AI that creates measurable business value.

This is a highly hands-on role. Great fit if you've been deploying real AI systems to production for years and want to build agentic products, not demos. Not a fit if your LLM experience stops at prototypes.

What You'll Do

- Design and develop AI-powered features and products end to end
- Build applications on LLMs (OpenAI, Anthropic, Gemini, open-source models) — prompt and tool-use design, information extraction, summarization, reasoning, and decision support
- Develop RAG systems: vector databases, embeddings, semantic search
- Design and implement AI agents for multi-step tasks — orchestration, tool integrations, planning, memory, and execution
- Build scalable AI services and APIs with evaluation frameworks, monitoring, and observability
- Optimize AI costs, latency, and reliability in production
- Build multimodal solutions that leverage vehicle inspection data, reports, and computer vision outputs




- Partner with Product and Engineering to identify AI opportunities; mentor other engineers on AI best practices

Success looks like: reliable, scalable AI services in production, reduced manual effort through intelligent automation, strong evaluation and monitoring practices, and rapid delivery of new AI capabilities. Must-Haves
- 5+ years of software engineering experience, including 3+ years building AI/ML-powered applications
- Proven experience deploying customer-facing AI systems to production
- Hands-on with major LLM APIs (OpenAI, Anthropic, Gemini) and/or open-source models (Llama, Mistral, Qwen, DeepSeek)
- Experience with at least one agent framework: LangGraph, LangChain, CrewAI, AutoGen, OpenAI Agents SDK, or MCP
- RAG architectures with vector databases (Pinecone, Weaviate, Qdrant, or pgvector)
- Strong backend engineering: Python (required), SQL, REST APIs, microservices — TypeScript preferred
- AWS (preferred), Docker, CI/CD
- Strong English — you'll collaborate directly with the U.S. team
- Located in Latin America with 4 hours of daily overlap with PST (7–11 AM)

Nice-to-Have Multimodal AI systems · combining Computer Vision and LLM workflows · fine-tuning open-source models · AI evaluation and testing methodologies · copilots, assistants, or agentic products · OCR and document understanding · knowledge graphs · AI safety and guardrails · Kubernetes · event-driven architectures · automotive or insurance tech · startup environments

We don't expect all of it. Strong on LLM apps, agents, RAG, and production backend engineering — apply.

Hiring Process

1. Apply — you'll be invited to a 20-minute AI interview
2. Latin Remote Workers interview — virtual, with our team
3. Final interviews — with the Self Inspection team

📌 Senior AI Engineer (Argentina)
🏢 Latin Remote Workers
📍 Argentina