ExperienceFounder and engineer2026-02 – present

Founder and engineer, Radicas

Building a FinOps platform for AI workloads — cost attribution, model routing and spend observability across LLM providers.

As of September 2026.

See the Radicas case study for the architecture and the decisions behind it.

Highlights

  • Cost attribution and spend observability across multiple LLM providers, broken down per feature and per tenant, with budget alerting and anomaly detection.

  • A routing layer that picks the model tier per request from task complexity, latency budget and cost ceiling.

  • Built the product's own AI layer with an eval harness gating every release and quality metrics tracked per commit.

Details

Employer
Radicas
Location
Turin, remote
Skills
Agent-assisted deliveryFinOps for AILLM observability and tracingModel routingEval harnesses and regression testingPython and FastAPIMulti-tenant SaaS architecture

Sources