We are redirecting you to the source. If you are not redirected in 3 seconds, please click here.

AI Engineer - LATAM at Space Inch. Space Inch is on a new mission, and we’re looking for AI experts and enthusiasts to join us!. . We’re building . the next generation of B2B AI experiences. , and we need . an AI engineer. to build, own, and operate . production-ready LLM-powered services end-to-end. . You will build and operate fast, reliable AI systems that power core platform features, enabling accurate, data-grounded recommendations and intelligent workflows with production-grade performance and reliability at scale.. We’re expanding our team and . bringing on multiple teammates. to contribute across multiple projects built on this stack.. Our Mission, Vision, and Values. At Space Inch, we prioritize alignment with our clients and team, ensuring a deep understanding of their needs. We are committed to delivering exceptional work while supporting the personal and professional growth of our team members. Every team member has access to an executive coach as part of this commitment.. About working at Space Inch. Our team (70+ people) is primarily based in Croatia, with members in South America, Serbia, and the US. While focus is on working remotely, we do have an office in Zagreb for those who prefer a hybrid approach and are located nearby.. Occasional travel may be required, including annual company retreats in Croatia.. We work on end-to-end projects with long-term vision. We strongly support work/life balance for our team members. Our ideal candidate's core tech stack:. Languages & APIs: . Python (FastAPI), TypeScript (Node/Nest BFF), REST/GraphQL, WebSocket/SSE. Python + FastAPI. production experience (async, dependency injection, testing).. Comfortable integrating with . TypeScript/Node. Built APIs with . REST/GraphQL. and at least one streaming pattern (. SSE/WebSocket. ).. LLM & RAG:. embedding stores (pgvector / OpenSearch / etc), chunking strategies, re-rank, hybrid search; prompt tooling & templates; guardrails. Observability & quality: . structured logging, tracing, metrics; experiment/eval tooling (e.g., Langfuse-style telemetry), offline/online A/Bs. Data & pipelines:. robust CSV/Sheets ingestion, schema validation, PII handling, backfills, scheduled jobs. Agentic experience (not day-one usage):. familiarity with . MCP . and agent frameworks, tool design, constrained execution, and safe planning, so you can leverage them when they’re the right fit. Proficiency in both spoken and written English. Candidates must be located within the LATAM region. Nice to have. LLM serving optimization (vLLM, TensorRT-LLM), quantization/LoRA know-how. Retrieval eval frameworks, cross-encoder rerankers, response grading. Experience with cost controls, token budgeting, and prompt compression. Serving & infra:. Docker, Kubernetes, CI/CD; model gateways (e.g., LiteLLM/vLLM) and caching; object storage (S3-compatible); message bus (Kafka or equivalent). Security & privacy:. tenant-aware access controls, secrets management, audit logs, privacy and safety red-teaming basics. Qualifications. 4-6+ years software engineering (product environments). , ideally with hands-on experience in shipping LLM/GenAI to production. Proven track record owning services end-to-end (design, implementation, rollout, monitoring, and iteration). Clear writing, pragmatic decision-making, and comfort collaborating with Mobile, Backend, and Ops (Dev/LLM). Experience with technologies . Qualities for success. Proactive, solutions-driven mindset. Strong attention to detail and code quality. Comfortable making technical decisions independently. Passion for learning and improving. Ownership mentality, i. e. you care about the end product. Company Location: Brazil.