Skip to content
View indianeagle4599's full-sized avatar

Highlights

  • Pro

Block or report indianeagle4599

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
indianeagle4599/README.md

Hitesh Goyal

Applied AI Engineer · Bengaluru, India

🟢 Open to Freelance and Full-time positions

Portfolio · Resume · Book a call · LinkedIn

I build and evaluate real-world AI systems across computer vision, speech, multimodal retrieval, LLM systems, and infrastructure.

Good ML starts with understanding the data: what it represents, where it falls short, and what the problem actually needs. I prefer to start simple, test assumptions, measure what matters, and change course when the evidence calls for it.

I work across the full path from data preparation and experimentation to evaluation, deployment, and usable interfaces, with real constraints such as latency, compute, data quality, and measurable performance in mind.

Best fit: small or founding teams where I can own an ambiguous AI/product problem and help turn it into a working system. If you know a team working on video analytics, speech/DSP, multimodal or LLM/retrieval systems, AI evaluation, or an AI-heavy product, an introduction is welcome.

What I work on

  • Computer vision & video analytics — detection, segmentation, temporal processing, low-latency inference
  • Multimodal & LLM systems — VLM pipelines, retrieval, structured extraction, embeddings and vector search
  • Speech & DSP — ASR evaluation, audio processing, reconstructed-phase-space features
  • Evaluation & reliability — benchmark design, reference-data validation, leakage detection, root-cause debugging
  • Applied AI products — end-to-end systems, APIs, dashboards, deployment, and agent-assisted development

Selected work

  • AudioBench — speech-model evaluation workbench with dataset curation, local/cloud job orchestration, persistent results, and layered performance analysis
  • AfterSight / Media Search Engine — multimodal media retrieval across semantic, OCR, contextual, metadata, and chronological signals
  • Pixtyle — image/video stylisation using classical CV, DSP, NumPy/PyTorch backends, and GPU acceleration
  • OS Toolkit — filesystem analysis, safe transfer tooling, concurrency, and repeatable performance benchmarking

Background

M.Sc. Artificial Intelligence, Nanyang Technological University. Experience across applied AI and R&D at Amplify Dental, Hummingbird Bioscience, Tata Elxsi, and Samsung R&D.

Connect

Pinned Loading

  1. Media-Search-Engine Media-Search-Engine Public

    Image-first media search engine that extracts metadata-aware visual descriptions, indexes them across semantic, lexical, OCR, and chronological retrieval surfaces, then fuses results for richer loc…

    Python

  2. Pixtyle Pixtyle Public

    Turn real-world photos and videos into stylised, flat-colour living wallpapers using colour clustering, Fourier filtering, edge enhancement, and optional super-resolution upscaling.

    Python

  3. ask-krishna ask-krishna Public

    Quiet Bhagavad Gita reflection in the browser — mantra, pause, five passages. Fully static; vanilla JS and localStorage only.

    JavaScript

  4. flodoro flodoro Public

    Serverless, local-first Pomodoro timer and task manager with configurable sessions, focused notification settings, local task/history tracking, ambient audio playlists, theme controls, and demo scr…

    JavaScript

  5. os-toolkit os-toolkit Public

    Python-first OS toolkit for filesystem analysis, safe file transfer, migration planning, and developer workflow automation.

    Python