We build managed cloud platforms and ML infrastructure for complex data processing — from radio signal analysis to image anomaly detection. Production-grade SaaS, backed by open-source engines.
Open-source core. Managed cloud. Built for production.
Products
Intelligent tools for complex data — optical image analysis and radio signal processing, powered by ML and delivered as managed cloud platforms.
v1.1.0
AI-powered astronomical image anomaly detection using Vision Transformers, YOLO, and out-of-distribution detection.
v0.1.0
Rust-accelerated radio signal analysis with CNN+Transformer ML classification, 45x faster than turboSETI.
Purpose
Modern astronomical surveys generate 20 terabytes of data per night in optical images alone. Radio observatories like the Breakthrough Listen program produce millions of signal candidates across thousands of observation files. The bottleneck in astronomy has shifted from collecting data to analysing it. Anomalies — gravitational lenses, transient events, narrowband signals — slip through unnoticed.
We built AstroLens for optical sky survey analysis (Vision Transformers, YOLO, OOD detection) and MitraSETI for radio signal processing (Rust de-Doppler, CNN+Transformer classification). Together, they form the foundation of a cloud platform designed for high-volume, complex data processing — with the same architecture patterns applicable to geoscience, remote sensing, and beyond.
These tools demonstrate what we deliver professionally: end-to-end ML systems that move from a research concept to a production-grade, self-operating pipeline. The same engineering approach — designing for autonomy, building self-correcting feedback loops, instrumenting for observability — applies to any domain where organisations need to extract insight from large-scale data streams.
Full-spectrum astronomical analysis. AstroLens scans images for anomalies; MitraSETI processes radio signals for candidate signal detection. Future versions unify both on a single sky map.
Both tools are validated against real data. AstroLens recovered 269 known objects. MitraSETI detected Voyager-1 at 45x the speed of existing tools across 2,200 BL files.
The architecture patterns — streaming ML pipelines, Rust acceleration, self-correcting thresholds, autonomous operation — apply to any domain that processes high-volume data at scale.
Results
Combined results from optical and radio analysis — autonomous, validated, at scale.
Technology
Two intelligent pipelines covering the full electromagnetic spectrum — optical images and radio signals.
About
Technical Director -- Cloud, DevOps & Platform Engineering
Saman is a specialist in AWS Cloud and DevOps with 10+ years of experience delivering cloud platform consultancy and production-grade solutions for large organisations. He designs and automates secure, scalable AWS architectures end-to-end—covering solution design, CI/CD, platform engineering, and technical leadership—with a focus on building reusable patterns that teams can ship, operate, and evolve with confidence.
Before specialising in cloud, Saman built a strong software engineering foundation across Linux embedded systems, monitoring applications, and cross-platform desktop development using Qt, including low-level networking and protocol implementation in C. That mix of deep engineering roots and modern AWS delivery means he brings practical judgement to every engagement—balancing speed, reliability, security, and cost without the hype.
Philosophy
Science advances fastest when tools are open, reproducible, and accessible to everyone.
Transparent and reproducible research that anyone can verify, audit, and build upon.
No cloud dependency required. Run everything on your own hardware, with your own data.
Designed to plug into existing research pipelines with standard interfaces and formats.
Community-driven development and improvement. Contributions, feedback, and collaboration welcome.
Now Live
MitraSETI Cloud is a fully managed SaaS platform for radio astronomy signal analysis. Upload your observation data, run automated detection and ML classification pipelines, and visualise results — all in your browser. No infrastructure setup, no installation required.
Upload .h5, .fil, .fits, and .hdf5 files up to 1 GB. Automated pipelines handle the rest.
AstroLens-powered CNN + Transformer models classify signals and flag anomalies automatically.
Waterfall plots, signal galleries, and pipeline monitoring — real-time in your browser.
Free tier available • No credit card required • Researcher and Institution tiers for larger workloads
Get in Touch
Open to research collaborations, industry partnerships, and commercial engagements.
Partner on astronomical surveys, anomaly detection research, or radio signal analysis projects.
Run MitraSETI at scale on managed cloud infrastructure. Start free or contact us for team and institution plans.
Custom ML pipelines, data processing systems, and infrastructure tailored to your research needs.
