Senior Backend Engineer — Go | Data + LLM (Remote — LATAM Only)

Location: Remote — Latin America (LATAM Only)

Employment type: Part Time | Remote

About Us

We’re building next-generation data and AI infrastructure that powers intelligent products through real-time knowledge graphs, vector search, and large-language-model (LLM) capabilities.

Our backend team focuses on scalability, performance, and developer experience. You’ll join a fast-moving, engineering-driven environment where impact is immediate and measurable.

The Role

We’re looking for a Senior Backend Engineer with solid Go (or equivalent) experience who can design and implement high-throughput data ingestion pipelines, knowledge-graph APIs, and LLM-driven features (RAG, embeddings, semantic search).

You’ll collaborate closely with data, ML, and product teams to deliver backend services that power AI-enabled applications used globally.

What You’ll Do

• Design, build, and scale real-time data ingestion and ETL pipelines from multiple sources (APIs, scrapers, third-party integrations).
• Architect and maintain our knowledge graph and semantic search infrastructure.
• Implement and optimize RAG / embedding pipelines using vector databases and Elasticsearch.
• Develop reliable backend services in Go (Golang) — migrate legacy Python/Flask components when needed.
• Ensure performance, resilience, and observability of distributed systems (monitoring, logging, tracing).
• Partner cross-functionally with ML, Product, and Infrastructure teams to design new AI-driven features.
• Contribute to technical roadmap, best practices, and internal tooling.

Must-Have Skills

• 3 – 8 years of professional backend experience.
• Expertise in Go / Golang (or strong background in Python, Java, C++ or C#).
• Strong knowledge of PostgreSQL / Postgres and Elasticsearch (or similar).
• Hands-on experience with data ingestion, pipelines, or ETL frameworks.
• Experience integrating LLMs, embeddings, or vector search.
• Proficiency with APIs, microservices, and event-driven architectures.
• Solid understanding of distributed systems, caching, and performance tuning.
• English working proficiency.

Nice-to-Haves

• Experience with RAG architectures, semantic search, or prompt engineering.
• Knowledge of containerization (Docker, Kubernetes) and CI/CD pipelines.
• Background in NLP, ML, or knowledge-graph projects.
• Previous startup or early-stage product experience.