About
👋 Hi, I’m Akash, an applied researcher/engineer with experience in speech, audio (at Microsoft), and most recently multi-modal document understanding and retrieval (at Contextual AI). This incidentally completes the trio of audio, vision & text AI multimodality. :)
I’m currently on a sabbatical. After moving to the USA for grad school ~10 years ago, I decided to take a break to reflect, recharge and tinker before setting sail again. More on this here shortly!
Work
Contextual AI
[2024-25]
Wrangled millions of pages to land the first $ millions in enterprise contracts :)
- System development (0→1)
- Designed core multimodal document understanding (parsing + ETL index) used by retrieval agents for all customers in production
- Ingesting O(billion) tokens of multimodal documents with complex layouts, tables, graphics, metadata
- Shipped as a distributed async service with multiple stages (CPU, GPU and VLM API). I owned system quality and core modules, and co-led architecture with a platform lead
- Applied research: harness and eval design, token-efficient retrieval
- Built core harness combining parsing tools, custom segmentation models and VLM/LLM modules for auditable OCR with bbox provenance and minimal hallucination
- Developed composable ingest-time ETL workflows enabling efficient retrieval beyond point queries (à la llm-wiki)
-
Blog: Token-efficient GraphRAG Demo: 250 page PDF chat in Cursor
- Tech Lead Manager
- PoC with Product/GTM/Marketing across company; Interviewed candidates, led team of 3
- Critical in landing company’s first multi-million $ enterprise contract with Qualcomm
Microsoft
[2018-23]
Fun fact: ~6M hours of monthly traffic equals 1 *year* of conversations transcribed per hour!
- Model development: state-of-art transcription designed for scale [O(10 million) hrs/mo]
- Shipped both batch and streaming models to Azure Batch, Microsoft Word, and Microsoft Teams
- Conformer batch model (Whisper-comparable) optimized to run at 50x realtime
- Applied research: diarized multi-speaker multi-mic transcription
- Shipped diarized in-conference room transcription device covered by The Verge
- Lead contributor: ASR training recipes, evaluation metrics, cross-system error analysis
- Research engineering: data pipelines, distributed training, inference
- Sped up O(1e20) FLOP training on low-cost V100 GPUs to run in <1 week
- Fixed inference bottlenecks leveraging NVIDIA/ONNX profiling tools, saving $ millions
- Other Links:
‘Graduated’ as one of the few non-speech-PhD senior members on the team :)
For more details, see my resume.
Misc
Open source
- [2026] 🎙️ Self-study: efficient audio generation (github, ongoing). Speculative decoding with relaxed acceptance on single-codebook TTS (Chatterbox-TTS); Meanflow distillation of FSQ token flow decoder for 2x faster local inference (Voxtral-TTS).
- [2023] 🐥🗣️ Contributed to whisper.cpp (50k+ stars). tinydiarize is a lightweight extension of OpenAI’s Whisper model for speaker diarization, runnable on MacBooks/iPhones.
- [2020/26] 🐋 Co-founded OrcaHello, a real-time alert system listening for endangered orca calls 24/7 at underwater “hydrophones” in the Pacific Northwest. Awarded a $30k AI for Earth grant; interviewed in Mongabay News.
- [2018] 🗣️ Built Attention, I’m Trying to Speak: speech synthesis with just $75 of compute. Got to fist-bump Richard Socher for Stanford CS224n project award :).
Other
- [2025/26] Peer reviewer for ICASSP conference, TMLR journal, and NeurIPS, CVPR workshops.
- [2016/17] Wrote case studies on the music streaming industry while studying business/tech strategy at Stanford MS&E.
- [2014] Organized (at the time) Chennai’s largest EDM gig - with 5k+ attendees, during my undergrad at IIT Madras/Chennai.