We are looking for a senior-level AI-focused Software Engineer based in Ecuador to work closely with a Lead Engineer building AI-powered backend systems and agent-driven workflows.

This role is ideal for an engineer who already has hands-on experience working with LLMs and AI APIs and wants to deepen their skills by implementing real production AI systems, not just demos or prototypes.

You will not be responsible for defining AI architecture alone, but you must be comfortable building, integrating, and iterating on AI-driven features under senior guidance.

What You'll Be Working On

• Implementing AI-powered backend features using LLM APIs

• Supporting agent workflows and AI orchestration logic

• Prompt engineering and structured output handling

• Integrating AI services into production backend systems

• Managing AI-related data flows, embeddings, and vector storage

• Monitoring AI behavior, latency, and cost usage

• Improving reliability and safety of AI outputs

Core Responsibilities

• Build backend services in Python that integrate AI models and APIs

• Implement LLM calls using providers such as OpenAI or similar

• Work with embeddings, vector databases, and retrieval workflows

• Support multi-step AI or agent pipelines defined by senior engineers

• Handle structured responses, validation, retries, and fallbacks

• Collaborate on prompt design and iteration

• Write tests and documentation for AI-driven features

• Debug and improve AI behavior in production environments

Required Skills & Experience

• 5+ years of professional software engineering experience
• Strong Python skills
• Hands-on experience with AI / LLM APIs in real projects
• Experience with prompt engineering and model configuration
• Familiarity with embeddings and semantic search concepts
• Experience building backend APIs (FastAPI or similar)
• Comfortable working with production data and edge cases
• Strong ENGLISH communication skills and ability to work under technical direction
• Experience with agent frameworks (LangGraph, LangChain agents, or similar)
• Multi-step AI pipeline or orchestration experience
• Exposure to vector databases (Pinecone, Weaviate, FAISS, etc.)

Nice to Have

• Experience with async Python or background job systems
• Understanding of AI cost, latency, and performance tradeoffs
• Interest in AI safety, evaluation, or observability

What Success Looks Like

• You can independently implement AI features scoped by a lead engineer

• You understand how AI systems behave in production, not just demos

• You actively improve prompt quality, reliability, and output structure

• You become faster and more autonomous over time

• You contribute meaningfully to AI-driven system evolution

Why This Role

• Real-world AI engineering, not research or toy projects

• Direct mentorship from a senior / lead AI engineer

• Exposure to agent-based systems and modern AI stacks

• Clear growth path into senior AI engineering roles

• Competitive LATAM compensation with long-term growth