Local inference
Private inference infrastructure, owned outright rather than rented: local models across multi-GPU servers, with task-based routing between them.
Learn moreI’m Sanjay. AI Systems Engineer
I design, build and run AI infrastructure, real-time platforms and automation—from first sketch to production.
What I do
Architecture, infrastructure, code, deployment and the pager afterwards. Systems fail at the seams between people.

Private inference infrastructure, owned outright rather than rented: local models across multi-GPU servers, with task-based routing between them.
Learn moreHealth, alerting and honest failure states. Failover, back-pressure and recovery paths go in at the start.
Learn moreServers, network and storage sized to the real workload, with power and thermal headroom under sustained load.
Learn moreInfrastructure only one person can run is a liability. The goal is an interface someone else can use safely.
Learn moreWhat I build
From the model to the interface. Every layer, working together.
Private inference infrastructure, owned outright rather than rented.
Live video and audio treated as an engineering problem with a latency budget.
Repetitive operational work turned into supervised, recoverable pipelines.
Making complex infrastructure operable by people who never read a log file.
The layer everything else quietly depends on.
Accountable for the outcome, not just the commit.
Selected systems
Anonymised systems. Real architecture, decisions and ownership.





From idea to production
Most technical work stalls between the whiteboard and the server. I stay responsible for the whole line.
How I work
Systems that are owned, verified and operable.
Six things I hold to when deciding how a system should be built, and what to do when the pressure is on to cut a corner.
Technical range
Grouped by what it is used for, not rated out of ten.
| Area | Focus | Tools and techniques |
|---|---|---|
| 01Languages | primary | |
| 02Frontend | interfaces | |
| 03Backend | services | |
| 04AI & ML tooling | inference | |
| 05Automation | orchestration | |
| 06Infrastructure | platform |
Tell me what you’re imagining. We’ll work out what it takes to build it.