Julian Francisco

AI/ML Engineer @nvidia

[Julian Francisco @_p0lymath_]

@shaunakjoshi 👀

[Julian Francisco @_p0lymath_]

@aarush Prove it 😉

[Genspark @genspark_ai]

We integrated Kimi K2 Powered by Groq into Genspark AI Developer!🚀

Our CTO Kay Zhu and Groq's Field CTO Christopher Stephens ran Genspark AI Developer + Kimi K2 against Lovable in a game dev challenge.

🌟The results were encouraging: 4x faster and 5x cheaper!🌟

The real win? People who've never touched code are now shipping actual applications. Groq's lightning-fast inference is what makes this level of performance possible.

Thanks to the @GroqInc team for being great partners. Looking forward to seeing what our users build with this.

[Julian Francisco @_p0lymath_]

Faster AI inference is an OP unlock for devs/companies building with AI. Better user experience, more time to refine and improve outputs, and cheaper inference are just a few of the many benefits.
Unlock your applications with @GroqInc's Fast AI Inference.

[Groq Inc @GroqInc]

snake, but build it 4x faster and 5x cheaper.

@genspark_ai on Groq:

[Julian Francisco @_p0lymath_]

Come join me at VapiCon '25 to hear how @GroqInc cloud is powering real-time voice applications, and learn how to build your own! ⚡️🔥

[Vapi @Vapi_AI]

The VapiCon agenda is here! A day built to showcase the most exciting voices, ideas, and innovations in voice AI.

This is the moment the voice AI community has been waiting for.

[Ben Ankiel @benankiel]

We just launched remote MCP support on @GroqInc.

This is such a powerful tool for agentic workflows.

Just tell it to "create a customer" and watch @Stripe's MCP server work for you.

Try out the demo and get the code below.👇

[Shaunak Joshi @shaunakjoshi]

🚀 Remote MCP just dropped on Groq! @p0 and @huggingface integrations showcase Groq's lightning-fast agent capabilities. OpenAI compatible, seamless integration.

[Julian Francisco @_p0lymath_]

Easily build mcp-integrated agents.
Groq + Remote MCP 🔥

[Groq Inc @GroqInc]

🚨Remote MCP is live on GroqCloud

- Connect to any tool
- Share context seamlessly
- All OpenAI compatible
- Run faster at lower cost

The universal bridge your agents needed

In preview now👇

[Groq Inc @GroqInc]

🚨Today we’re rolling out Prompt Caching on GroqCloud.

Keep hot prompts in memory, cut cached token costs by 50% and slash latency.

Faster response, smarter inference.
Learn more 👇

[Groq Inc @GroqInc]

Meet your full-stack AI assistant, powered by OpenAI’s new open gpt-oss models (20B + 120B) and Groq.

Includes search, code execution, STT/TTS, code-gen editor, AI notes, and custom tool calling.

Build Fast.