AS

Akul Mallayya Swami

Independent Researcher in Runtime Assurance and Safety Critical Edge ML Systems

Runtime Assurance Trustworthy Edge ML Timing Validation Safety Critical Software IEC 62304 · ISO 14971

Akul Mallayya Swami is an independent researcher and safety critical embedded systems engineer focused on deployment assurance, runtime trustworthiness, and timing validation for edge machine learning systems operating in real world environments.

His research investigates how AI systems can remain statistically correct while becoming temporally unreliable under deployment interference, a failure mode that is often under evaluated in current ML validation pipelines.

His current work focuses on hardware validated timing analysis, runtime timing fidelity monitoring, and interference aware deployment evaluation for edge AI systems using externally calibrated measurement methodologies.

Current research thesis: timing trustworthiness should be treated as a first class deployment assurance property for edge ML systems, separate from statistical accuracy.
TFS Guard
Runtime timing fidelity monitoring

TFS Guard studies how deployed edge ML systems can preserve output correctness while violating timing assumptions under runtime interference. The work evaluates timing drift, deadline violation behavior, and hardware validated runtime observability.

Edge ML Deployment Assurance
Jetson Orin Nano · Coral Dev Board Micro · Saleae timing reference

Comparative experiments examine shared Linux inference environments and more isolated edge inference paths to evaluate how architecture affects temporal reliability under realistic contention.

Runtime assurance for deployed edge ML systems
Timing trustworthiness and temporal reliability in AI deployment
Hardware validated latency analysis and external timing calibration
Interference aware deployment validation methodologies
Safety critical embedded software verification
Standards aligned software assurance under IEC 62304 and ISO 14971
Preprints and Workshop Submissions
In progress

Research manuscripts and preprints focus on deployment timing validation, runtime trustworthiness, and externally calibrated timing measurement for edge ML systems.

Open Research Infrastructure
Reproducibility artifacts

Public repositories are being structured around experiment protocols, timing logs, analysis scripts, hardware calibration notes, and reproducible edge ML timing evaluations.

Safety Critical Medical Device Systems
Embedded software engineering for FDA regulated medical device environments
Work involving runtime reliability, verification workflows, fault analysis, risk management, and standards aligned development practices for high reliability software systems.
Current
Embedded AI and Edge Systems
Deployment timing validation and runtime observability
Research and development involving embedded inference systems, hardware validated timing analysis, interference aware execution, and runtime monitoring of deployed edge AI systems.
Low Power and Wireless Embedded Systems
Resource constrained device software and connected embedded platforms
Experience with ultra low power systems, wireless communication, embedded firmware, and constrained edge architectures.
Master of Science
Computer Engineering
University of Massachusetts Lowell · 2017
Bachelor of Science
Electronics and Telecommunication Engineering
University of Pune · 2015
IEC 62304
ISO 14971 Risk Management
Software as a Medical Device
Safety Critical Embedded Software
Runtime Monitoring
Hardware Validated Timing