Headline

AI Engineer @ Platy Studio | Generative AI | LLMs | AI Agents | Speech AI | FastAPI | Python | Open Source AI

About

I'm an AI Engineer passionate about building production-grade Generative AI applications that solve real-world problems. Over the past 2+ years, I've designed and deployed scalable AI systems spanning Speech AI, Large Language Models (LLMs), AI agents, and backend infrastructure. My work goes beyond integrating AI APIs—I build end-to-end AI products, from model orchestration and inference pipelines to distributed processing, deployment, and production optimization. At Platy Studio, I develop multilingual AI solutions that combine Automatic Speech Recognition (ASR), Speaker Diarization, Voice Activity Detection (VAD), Machine Translation, Text-to-Speech (TTS), and media processing into scalable production workflows. I work extensively with asynchronous architectures using FastAPI, Celery, Redis, PostgreSQL, Docker, and GPU-accelerated AI inference. Some areas I enjoy working on include: • Generative AI & LLM Applications • Agentic AI Systems & Multi-Agent Workflows • Speech AI (ASR, TTS, Speaker Diarization) • Retrieval-Augmented Generation (RAG) • AI Backend Architecture • Production AI Infrastructure • Distributed Task Processing • Performance Optimization & Scalable AI Pipelines Tech Stack: Python • FastAPI • LangChain • LangGraph • OpenAI • Hugging Face • Whisper • Qwen ASR • PyTorch • Celery • Redis • PostgreSQL • Docker • React • Next.js • Linux I enjoy solving challenging engineering problems, sharing technical learnings through blogs, and building AI products that are reliable, scalable, and ready for production. I'm always interested in collaborating on innovative AI projects and connecting with engineers working in the Generative AI ecosystem.

Location

Ganjam

AI stack

antigravity

claude code

codex

cursor

elevenlabs

Roo Code

Work experience

AI Engineer at Platy.Studio, May 2024 - Present · 2 yrs 5 mos, Seattle, WA, AI Engineer | Platy Studio Building production-ready AI applications focused on Generative AI, Speech AI, and scalable backend systems. I work across the complete AI lifecycle—from AI model integration and inference pipelines to distributed processing, backend architecture, and deployment. • Architected and developed a multilingual AI dubbing platform for long-form audio and video processing using modern Speech AI and Generative AI technologies. • Designed scalable AI pipelines integrating Automatic Speech Recognition (ASR), Speaker Diarization, Voice Activity Detection (VAD), Machine Translation, Text-to-Speech (TTS), and subtitle generation. • Built production-grade backend services using Python, FastAPI, PostgreSQL, Redis, Celery, Docker, and Nginx to support high-performance asynchronous AI workloads. • Integrated and optimized state-of-the-art AI models including Whisper, Qwen ASR, Demucs, and open-source TTS models for multilingual speech processing. • Engineered efficient processing workflows for long-duration media through intelligent segmentation, parallel execution, task orchestration, and fault-tolerant pipelines. • Improved AI inference reliability by redesigning asynchronous execution patterns, implementing retry strategies, distributed background processing, and robust error recovery. • Developed RESTful APIs powering AI workflows consumed by React and Next.js applications. • Worked extensively on GPU-accelerated inference, media processing, FFmpeg automation, audio preprocessing, and AI model optimization. • Designed scalable database schemas and backend architectures for transcription, translation, and media management systems. • Collaborated closely with product, frontend, and backend teams to deliver scalable, maintainable, and production-ready AI solutions. Tech Stack: Python | FastAPI | | LLMs | Speech AI | Whisper | Qwen ASR | Celery | Redis | PostgreSQL | FFmpeg | React | Next.js | Linux | REST APIs

Frontend Developer at DigitalDose, Feb 2024 - Apr 2024 · 3 mos, Mumbai, Maharashtra, India, 1) Assisted in the development of frontend features and functionalities for client's web applications, under the guidance of senior developers. 2) Contributed to the optimization of existing codebase for improved performance and maintainability. 3) Participated in code reviews and provided feedback on peers' code, fostering a culture of collaboration and continuous improvement.

Frontend Developer at ARRORA, Aug 2023 - Feb 2024 · 7 mos, Bengaluru, Karnataka, India, 1) Designed and developed new web pages to visually represent business revenue data using React Js enhancing the website's functionality and providing stakeholders with intuitive insights into financial performance. 2) Leveraged data visualization libraries such as Apex.chart or Chart.js, Material UI to create dynamic and interactive graphical representations of revenue trends, empowering users to analyze and interpret financial data effectively. 3) Collaborated remotely with stakeholders and the development team to gather requirements, iterate on design mockups, and seamlessly integrate revenue visualization pages into the existing website infrastructure, ensuring consistency in style and performance across different browsers and devices.

Education

Data science, Alma Better

M.sc, Physics, Indian Institute of Technology (Indian School of Mines), Dhanbad

Public links

github: https://github.com/Situn09

leetcode: https://leetcode.com/Situn09

linkedin.com: https://www.linkedin.com/safety/go/?url=https%3A%2F%2Findependent-developer%2Ehashnode%2Edev&urlhash=YhdC&mt=a6LliDy7Fd68S9jgFlmLaLJzWLw8iFF-hwN7MLjZcfHYbWUKxxYrnXIsUY_omddPjQcbS69JIQ7MG-eef1GdMI-_RZw&isSdui=true