tinytera

SEEKING WORK | San Francisco, CA | REMOTE | CONTRACT Willing to relocate: Yes

Location: USA / Canada

Hello there, I have over 11 years in experience in backend engineering, and am expert in creating Generative AI based solutions. Some notable projects include:

1. AI YouTube short creator with 20k daily active users.

2. AI storyboarding tool with 10k ARR.

3. Various Chatbots on platforms like WhatsApp, Telegram, Slack and Matrix.

4. Cloud migration project involving PB of data for a flagship RDP product.

5. COVID platform creation that helped save thousands of lives in North America

Technologies:

AI/ML: Python, TypeScript, Streamlit, Stable Diffusion, LLM, Pandas, Langchain, CrewAI, Groq

API: FastAPI, Flask, Django, Express

Cloud: Terraform, AWS, GCP, Azure, Serverless

DevOps: TeamCity, OctopusCI, DataDog, Jenkins

Data: MySQL, RabbitMQ, Cassandra, Hadoop, MongoDB, Postgres, Redis, DynamoDB

Contact in profile. Have a great day!

SEEKING WORK | San Francisco, CA | REMOTE | CONTRACT

Willing to relocate: Yes

Location: USA / Canada

Hello there, I have over 6 years in contracting experience, and expert in creating Generative AI based solutions. Some notable projects include:

1. AI YouTube short creator with 20k daily active users.

2. AI storyboarding tool with 10k ARR.

3. Various Chatbots on platforms like WhatsApp, Telegram, Slack and Matrix.

4. Cloud migration project involving PB of data for a flagship RDP product.

5. COVID platform creation that helped save thousands of lives in North America

Technologies:

AI/ML: Python, TypeScript, Streamlit, Stable Diffusion, LLM, Pandas, Langchain, CrewAI, Groq

API: FastAPI, Flask, Django, Express

Cloud: Terraform, AWS, GCP, Azure, Serverless

DevOps: TeamCity, OctopusCI, DataDog, Jenkins

Data: MySQL, RabbitMQ, Cassandra, Hadoop, MongoDB, Postgres, Redis, DynamoDB

Contact in profile. Have a great day!

Hi Peter, thanks for taking this. How feasible is it for a Canadian Citizen who has a software consulting service to apply for E2 visa? Is it worth pursuing? What things are important to keep in mind for that?

Location: San Francisco, CA

Remote: Yes

Willing to relocate: Yes

Technologies: Python (Django, Flask, FastAPI), TypeScript, Terraform, Ansible, Docker, AWS, GCP, Azure, Redis, Cassandra, PostgreSQL, MySQL, Jenkins, TeamCity, API, Grafana, Datadog, git, Kafka, MongoDB, RabbitMQ, Numpy, Pandas, Jupyter

Résumé/CV: https://drive.google.com/file/d/1DTkTDgRXpmwQ-eTCKCP8oBg2gj7...

Email:jd+hn<at>tinytera<dot>com

Hey brian, I remember you from https://news.ycombinator.com/item?id=37705445 and recently open sourced one part of that app here https://github.com/jaideep2/apinaio Its a set of docker images to simplify GenAI workflows, since its hard to setup workflow correctly, especially for stable diffusion models. Only works on CUDA hardware for now, but contributions welcome :)

This is great! I use ComfyUI extensively and will try this out. Its hard to setup workflow correctly for these Video diffusion models.

I recently built a set of docker images to simplify GenAI workflows. Check it out at https://github.com/jaideep2/apinaio

Only works on CUDA hardware for now, but contributions welcome :)

Looks pretty cool. Can anyone comment on how to hack together the opposite? That is, going from 2D object image to 3D rendering with in-painted background? Or is that not possible right now.

This is great! For remixing, are you guys actually saving the latent assets/embeddings? Or regenerating the music from some "seed"?

Thanks! Fixed. Btw the app is now hosted on https://topic2video.streamlit.app

Looks interesting. Do you have visualizations or examples on debugging audio embeddings (like https://huggingface.co/spaces/facebook/MusicGen) ?

Weird. Can you check if its getting caught in email filter by going to https://regex101.com/r/y8xh8k/1 and typing the email under TEST STRING?

Thanks for the feedback. Added those to the backlog. Unfortunately this app has pushed Streamlit to its limits. It works as intended as a MVP, but the next version architecture will be more scalable.

Pretty awesome for first Show HN. Multimodal search is very fascinating. I am using SDXL + LoRa model over here https://news.ycombinator.com/item?id=37696033

I am running JAX version of "ctoraman/hate-speech-bert" over here https://news.ycombinator.com/item?id=37696033 and its pretty efficient

This is actually pretty cool. I am hitting a limit with my elevenlabs subscription soon for this app https://news.ycombinator.com/item?id=37696033 Going to replace with yours to see how it goes. Cheers!

Hey try again with a similar topic, made some changes for better quality text and image generation.

Example “Some stunning facts about the universe” https://topic2clip.streamlit.app/?vid=7549e327-89f3-478d-9dc...

Fixed! Got hit with spammers. Email is required for now.

Hey thoroughly enjoyed it! keep it up.

Thanks for trying it out! Yeah its very basic as is, but in future I would want to create a multimodal model that can handle complex topics.

Yeah, thats an interesting use-case. For now its just merging the SDXL images using ffmpeg and adding narration. For intro videos it would need cooler transitions. Maybe in the next version.

Whoops, crashed for a bit. Now up again. Please comment if it goes down. Also, for those asking for the tech stack:

- OpenAI Instruct API for generating script

- SDXL model for generating images

- ElevenLabs API for narration

- Streamlit for hosting and UI

Hey this is great for the spare one I have.