Space Inch

Space Inch

Space Inch is a digital innovation agency specializing in web, mobile, and augmented and virtual reality applications. They are known for creating a variety of software, with a focus on iPhone, iPad, and Mac apps. Space Inch has found success as mobile...

Internet Software & Services
11-50
Founded 2011

Description

  • Build, own, and operate end-to-end LLM-powered services in production.
  • Develop fast and reliable AI systems that power core platform features.
  • Deliver accurate, data-grounded recommendations and intelligent workflows.
  • Implement and maintain observability, monitoring, and quality evaluation for AI services.
  • Design and support robust data ingestion, validation, and backfill pipelines.
  • Collaborate with Mobile, Backend, and Ops teams on product delivery and technical execution.
  • Roll out, monitor, and iterate on services after deployment.
  • Contribute to multiple projects across the company’s AI stack.
  • Apply agentic patterns, tool design, and safe execution approaches where appropriate.

Requirements

  • 4-6+ years of software engineering experience in product environments.
  • Hands-on experience shipping LLM/GenAI solutions to production is ideal.
  • Proven experience owning services end-to-end, including design, implementation, rollout, monitoring, and iteration.
  • Strong Python experience with FastAPI, including async patterns, dependency injection, and testing.
  • Comfortable working with TypeScript/Node-based APIs and integrating Python services with REST/GraphQL backends.
  • Experience with at least one streaming pattern such as SSE or WebSocket.
  • Experience with LLM and RAG components such as embedding stores, chunking strategies, hybrid search, reranking, prompt tooling, templates, and guardrails.
  • Experience with structured logging, tracing, metrics, and evaluation/telemetry tooling.
  • Experience with data ingestion and pipeline work, including CSV/Sheets ingestion, schema validation, PII handling, backfills, and scheduled jobs.
  • Proficiency in spoken and written English and residence within the LATAM region.
  • Nice to have: LLM serving optimization with vLLM or TensorRT-LLM, quantization, or LoRA.
  • Nice to have: retrieval evaluation frameworks, cross-encoder rerankers, and response grading.
  • Nice to have: cost controls, token budgeting, and prompt compression.
  • Nice to have: Docker, Kubernetes, CI/CD, model gateways, caching, object storage, and Kafka or similar messaging systems.
  • Nice to have: tenant-aware access controls, secrets management, audit logs, and basic privacy/safety red-teaming experience.

Benefits

  • Monthly B2B salary of USD 4,750-6,500 depending on experience and skills.
  • Remote-first work arrangement.
  • Wellness subsidy to support staying active.
  • 100% paid sick leave.
  • Annual health checkups.
  • Christmas bonus and referral bonus.
  • Education budget for learning and professional development.
  • Access to an executive coach as part of the company’s growth support.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Engineering Intern – Gen AI for FP&A Platform

Drivetrain 11-50 Capital Markets

Drivetrain is hiring a remote-first Engineering Intern to help build Generative AI features for its FP&A platform, with a focus on real-world enterprise automation projects.

Generative AI LLM System Design
0 minutes ago

AI Engineer Mid-SR

Metova 51-250 Internet Software & Services

AI Engineer para una empresa que desarrolla soluciones con agentes inteligentes e IA embebida en entornos empresariales, con foco en construir y desplegar productos conectados a sistemas internos y plataformas externas.

AWS Azure C# CI/CD Docker ERP FastAPI GCP Go gRPC Java Kubernetes LLM Microservices MLOps .NET NLP Python REST API
1 hour, 15 minutes ago

Junior AI Engineer - Computer Vision

Innovation Team 51-250 Internet Software & Services

InnovationTeam is hiring a Junior AI Engineer – Computer Vision to develop and deploy production-ready image and video analytics systems for real-world AI applications.

AWS Azure CNN Computer Vision Deep Learning Docker GCP Machine Learning MLOps OpenCV Python PyTorch TensorFlow
1 hour, 15 minutes ago

Engineering Intern – Gen AI for FP&A Platform

Drivetrain 11-50 Capital Markets

Drivetrain is hiring a remote Engineering Intern to help build and prototype Gen AI capabilities for its FP&A platform, working on real-world enterprise automation projects.

Generative AI LLM Machine Learning System Design
1 hour, 30 minutes ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers