9 days ago
Buenos Aires, ArgentinaSenior
Responsibilities
- Design, implement, and operate production-grade reusable AI capabilities and services for engineering and product teams.
- Build and evolve LLM gateways, proxies, model-routing mechanisms, prompt and context strategies, and agentic workflows.
- Create evaluation frameworks, golden sets, LLM-as-a-judge systems, guardrails, and observability pipelines for task success, latency, security, and token costs.
- Define production AI engineering standards covering automated testing, versioning, context segregation, and incident response.
- Own delivery from problem framing and architecture through implementation, deployment, monitoring, and iteration.
- Build internal tools, scripts, and intelligent workflows that reduce manual work and improve developer velocity.
Requirements
- 5+ years of experience delivering and operating production-grade systems in software engineering, AI engineering, or ML engineering.
- Advanced hands-on proficiency in Python, RESTful or asynchronous APIs, microservices, and AWS or GCP cloud services.
- Proven experience building reliable LLM applications, RAG pipelines, agent orchestration, and Model Context Protocol integrations.
- Hands-on experience with LLM proxies or gateways, model routing, evaluation harnesses, and AI observability tools.
- Ability to make architectural trade-offs across quality, latency, reliability, security, privacy, scalability, and cost.
- Advanced English proficiency and clear communication with cross-functional technical stakeholders.
- Experience with Docker, Kubernetes, and Terraform is preferred.
- Experience with internal developer platforms or developer tooling is preferred.
- Experience with prompt optimization, open-source model fine-tuning, or custom vector database indexing is preferred.
Benefits
- Long-term 100% remote engagement.
- High-impact strategic role focused on shared AI foundations and internal developer adoption.
- Collaborative international environment with senior technical leadership.
- High autonomy to research, prototype, and implement GenAI workflows.
- Competitive compensation and growth opportunities.
Tech Stack
Categories
