Where the future of AI compute is being defined and built, to unlock new levels of machine intelligence.
Santa Clara, CA
Joined December 2024
- Tweets37
- Following54
- Followers101
- Likes15
Our Chief Scientist @Shwetankumar on why on-device AI is stuck, and how EN100 fixes it.
The culprit: data movement. EN100 computes inside the memory cells, eliminating it entirely.
Full blog here: enchargeai.com/blog/the-pers…
"Instead of moving data to the processor, EnCharge performs the actual math inside the memory itself. This essentially eliminates the commute for data."
Moving data between memory and compute accounts for 60-80% of energy consumption in AI. @EnChargeAI accelerators use up to 20x less energy for AI workloads.
What becomes possible when powerful AI runs locally on any device?
Full conversation here: youtu.be/UrG_nF_RuqM?si=i1cz…
#EnChargeAI #AnalogInMemoryCompute #DecentralizedAI #AIintheAM
EnCharge AI retweeted
"how much can you integrate compute and memory together"
Naveen Verma, Co-founder & CEO of EnCharge AI @EnChargeAI, says the next bottleneck is not just chips — it's how tightly memory and compute can be fused.
"how does a fundamental technology like this become a critical unlock to doing that"
EnCharge AI retweeted
Join Nathan @labenz and Prakash @8teapi Friday 9am-11am PT as we host with
9.00am - @AnnapPatterson, CeramicAI
9.30am - Lukas Petersson @lukaspet, @andonlabs
10.00am - Zvi Mowshowitz, @TheZvi
10.30am - Naveen Verma, @EnChargeAI
See you on the stream!
xitter.cf/i/broadcasts/1AJEmODkn…
ENCharge AI’s Analog In-Memory Compute technology significantly reduces the power demand of data centers, laptops, workstations, robots and drones while also enabling secure localized data processing without a tradeoff in performance or efficiency.
"Making AI more efficient doesn't just improve a robot's brain; it can transform its whole body." - Max Maxfield
Full feature from @EEJournal linked below. eejournal.com/article/enchar…
“Data centers are juicy targets.”
Iran's drone strikes on @awscloud facilities in the Gulf disrupted services, highlighting the risks of concentrating AI infrastructure in one place.
Centralizing AI = centralized risk.
When intelligence depends on centralized systems, it creates something that can be found and targeted.
Edge and physical AI systems process data where it lives, reducing reliance on vulnerable infrastructure.
Technologies like EN100 from EnCharge AI support this shift.
Full story from @Axios here: axios.com/2026/04/01/iran-wa…
Our founder Naveen Verma's recent interview with SAE Media Group highlights how data movement drives inefficiency in today’s #AI systems.
@EnChargeAI's EN100 is different. It brings compute closer to where data lives.
The result:
• up to 20x lower power
• real-time performance
• AI that runs directly on-device
Read more about it here: mobilityengineeringtech.com/…
EnCharge AI retweeted
Most startups try to move fast.
Some of the best ones take their time.
Here is what @EnChargeAI can teach founders 🧵
Proud to see our debut accelerator EN100 in @EDNcom's Top 10 Edge AI Chips by @sallywf.
Using less power than a lightbulb, EN100 delivers 200+ TOPS of computing capacity to unlock the most advanced AI in every environment.
Read the full roundup: edn.com/top-10-edge-ai-chips…
Technological dexterity is a strategic imperative, per @CSIS, and long-game advantage comes from compounding cross-domain strengths.
Ultra-efficient AI compute sits at the center of that progress, and that's exactly what EnCharge has built.
enchargeai.com/news-and-publ…