About Nivii
At Nivii.ai, we're building a new way for teams to work with data. Instead of dashboards and traditional BI, we're creating an AI-powered platform that allows users to ask complex business questions in natural language and receive structured, explainable, and actionable answers.
Over the past year, we've moved from concept to production: a multi-agent system that is already being used in real decision-making workflows. We're now looking for a Software Engineer, AI/LLM Platform to help us scale, harden, and evolve the core systems that power this platform.
About The Role
This role is software-engineering-first, with AI and LLMs as core building blocks. You'll work very close to the product and the founders, owning critical parts of the platform end-to-end.
What You'll Do
- •Design, build, and own core platform services that power our AI/LLM workflows
- •Develop and operate LLM-based systems (e.g. text-to-SQL, reasoning agents, planners), with a strong focus on reliability, performance, and cost
- •Build and maintain backend services and APIs that orchestrate complex, multi-step AI pipelines
- •Work hands-on with Kubernetes-based infrastructure, including deployments, scaling, and debugging production issues
- •Contribute to DevOps and MLOps workflows: CI/CD, environments, monitoring, logging, and operational best practices
- •Collaborate on architectural decisions around observability, failure handling, evaluation, and system trade-offs
- •Work closely with founders and product to translate real business problems into robust technical solutions
What We're Looking For
- •4+ years of experience as a software engineer in backend, ML, or data-intensive systems
- •Strong software engineering mindset with proven experience shipping and maintaining production systems
- •Excellent Python skills and experience building backend services (FastAPI or similar)
- •Solid hands-on experience with Docker and Kubernetes in real-world environments
- •Basic to solid DevOps knowledge: CI/CD pipelines, cloud environments, logging, monitoring, and deployments
- •Experience with cloud platforms (AWS preferred)
- •Practical experience working with LLMs in applied settings (text-to-SQL, RAG, agent-based systems, or similar)
- •Ability to reason about and manage trade-offs (quality vs latency, cost vs performance, simplicity vs flexibility)
- •Strong communication skills in English
Bonus Points
- •Experience with SQL databases, data platforms, or vector databases
- •Experience designing evaluation frameworks for ML or LLM systems
- •Previous experience in early-stage startups or high-ownership teams
What We Offer
- •Work on a real AI/LLM platform in production, not demos or research projects
- •High ownership and direct impact on the core technology and product direction
- •Equity + competitive salary
- •Fast growth path into senior or leadership responsibilities as the team scales
- •Hybrid work model based in Buenos Aires