.png){kind=logo}
Daniel Luzzatto
Junior Machine Learning Engineer specializing in LLMs, computer vision, and robotics
Connect with Daniel
Daniel already has a relationship with Reval, so a warm intro from us gets a much better response than cold outreach.
Recommended
Already have an account?
About
Built and deployed an agentic, multimodal LLM system that automates privacy redaction pipelines (audio/video/tabular) using LangChain orchestration and a closed-loop self-correction design. Personally implemented and performance-optimized core CV tooling (face blurring with tracking/Kalman filter) achieving >100 FPS on CPU, and validated reliability with golden-dataset benchmarking across 100+ privacy intents and measurable redaction metrics.
Experience
Education
Key Strengths
- Built and deployed production agentic AI system for automated data privacy in smart environments
- Designed closed-loop retry architecture improving failure rate by ~24%
- Optimized face blurring pipeline to >100 FPS on CPU using detection every 5 frames + tracking + Kalman filter
- Strong evaluation discipline: 100+ privacy intents tested against a golden dataset with defined reliability metrics
- Pragmatic model selection balancing capability, latency, and cost (different LLMs per task)
- Effective LLM-tool integration via LangChain tool abstractions for CV/NLP redaction selection
- Clear communication process with non-technical stakeholders (simplifying inputs/outputs/constraints) and team cadence (weekly meetings, code review)
Discover more candidates like Daniel
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent