We are looking for senior AI Backend Engineer to join our team.

# Senior AI Backend Engineer – LLM Applications

**Company:** Asahan Tech Partners
**Location:** Latin America
**Work Arrangement:** Fully Remote
**Compensation:** USD $2,000–$4,000 per month

## About the Role

Asahan Tech Partners is looking for a **Senior AI Backend Engineer** based in Latin America to design and build scalable backend systems for LLM-powered applications.

You will work on production AI systems involving large language models, backend APIs, data processing, AI workflows, and cloud infrastructure. This role is ideal for an experienced backend engineer who understands how to integrate LLMs into reliable, secure, and maintainable applications.

## Responsibilities

* Design, build, and maintain backend services for LLM-powered applications.
* Develop scalable APIs and microservices for AI features.
* Integrate LLM providers and AI services into production systems.
* Build and improve retrieval-augmented generation pipelines.
* Implement document ingestion, text processing, embedding, and vector-search workflows.
* Design prompt-management and AI workflow systems.
* Improve the accuracy, reliability, latency, and cost efficiency of LLM applications.
* Build monitoring, logging, error-handling, and evaluation systems for AI outputs.
* Design secure data flows and protect sensitive application data.
* Work with relational databases, vector databases, caching systems, and message queues.
* Deploy and maintain backend services using cloud platforms and container technologies.
* Review code and contribute to technical architecture decisions.
* Collaborate remotely with developers, product stakeholders, and other team members.
* Troubleshoot production issues and improve overall system performance.

## Requirements

* At least 5 years of professional backend development experience.
* Strong experience with Python and modern backend frameworks such as FastAPI, Django, or Flask.
* Practical experience building or integrating LLM-powered applications.
* Experience working with LLM APIs such as OpenAI, Anthropic, Google Gemini, or similar platforms.
* Understanding of retrieval-augmented generation, embeddings, vector search, and prompt engineering.
* Experience designing REST APIs, microservices, and distributed backend systems.
* Strong knowledge of SQL databases such as PostgreSQL or MySQL.
* Experience with vector databases or search technologies such as Pinecone, Weaviate, Qdrant, Milvus, Elasticsearch, or pgvector.
* Experience with cloud platforms such as AWS, Google Cloud, or Microsoft Azure.
* Experience with Docker, Git, automated testing, and CI/CD workflows.
* Understanding of authentication, authorisation, API security, and data protection.
* Ability to write clean, maintainable, and well-tested code.
* Strong problem-solving and system-design skills.
* English fluency for technical discussions and remote collaboration.
* Ability to work independently in a fully remote environment.
* Must be based in Latin America.

## Preferred Qualifications

* Experience building production RAG systems.
* Experience with LLM evaluation, observability, guardrails, or hallucination reduction.
* Experience with LangChain, LlamaIndex, Semantic Kernel, or similar frameworks.
* Familiarity with agentic workflows and tool-calling systems.
* Experience with asynchronous processing and message brokers such as RabbitMQ, Kafka, or AWS SQS.
* Experience optimising LLM token usage, response time, and infrastructure costs.
* Previous experience working with international or distributed teams.

## What We Offer

* Fully remote work from anywhere in Latin America.
* Monthly compensation of USD $2,000–$4,000, depending on experience and technical ability.
* Opportunity to work on practical, production-focused LLM applications.
* Direct involvement in backend architecture and technical decisions.
* Collaboration with an international remote team.
* Long-term opportunities based on performance and project needs.

## How to Apply

Please submit your resume or professional profile along with a brief description of your experience building backend systems or LLM-powered applications.