Muhammad Asim is the founder and CEO of Devsort, a data science and software engineering company based in Islamabad, Pakistan. He founded Devsort with a focus on technically complex, high-stakes engineering work — the kind of project where the cost of getting it wrong is meaningful and the credibility of getting it right is verifiable.
The engagement that defines Devsort’s practice is a 2.5-year programme with PKG Health (now part of Empatica), a company that had developed FDA 510(k) cleared algorithms for monitoring movement disorders in Parkinson’s disease patients. When Asim’s team took on the engagement, the algorithms were frozen — implemented in four legacy languages, undocumented, and effectively unmaintainable under the regulatory constraints that governed any change. The brief was to refactor them without invalidating the certification. Six algorithms were refactored and validated in Python, extended to five wearable device platforms, and a subset deployed to embedded C on the Empatica device hardware.
The technical and regulatory experience from that engagement informs how Devsort approaches every project. Working under FDA 510(k), CE, and TGA frameworks over 2.5 years creates a specific kind of engineering discipline — one that treats documentation as a first-class deliverable, validates outputs against reference implementations rather than intuition, and understands that the constraints imposed by regulatory certification are the specification, not an obstacle.
Devsort’s work spans clinical algorithm development, wearable data science, embedded firmware, custom software, and web and mobile product development. The clinical-grade discipline developed through the PKG engagement applies across all of them — because the habits of rigour that regulatory work demands are useful regardless of whether a specific project is regulated.
Areas of expertise
Articles
Why clinical-grade algorithm development is different from regular software engineering
Regulatory certification changes what it means to write correct code. This is how the FDA 510(k) framework shaped our engineering practice over a 2.5-year engagement with PKG Health.
19 May 2026
Working on a clinical data science problem?
If your project involves regulated software, wearable algorithms, or embedded systems — we have done that work under real constraints. Tell us about it.
Start a conversation →