Rohith K Bobby
@rohithkbobby
I’m an ML & MLOps engineer building low-latency production voice AI with Kubernetes, GPU inference, and Ray.
What I'm looking for
I’m an ML & MLOps engineer focused on production voice AI, backend services, GPU-backed inference, and Kubernetes deployments. In my current role, I built low-latency voice AI pipelines with LiveKit and self-hosted ASR, LLM, and TTS services for production call handling.
I’ve served Parakeet ASR and Kokoro TTS on bare-metal L40S infrastructure using Kubernetes, KubeRay, Ray Serve, and Docker, validating performance with concurrency sweeps (e.g., 155 RPS ASR, p50 latency below 200ms) and strong transcription match across 2,400 test requests. I also developed an OCR pipeline, keyword extraction and article tagging systems, and Indic-language translation/summarization workflows as an ML intern—work that reinforced my preference for measurable, production-ready results.
Experience
Work history, roles, and key accomplishments
ML & MLOps Engineer
GenerativeStudio.dev
Dec 2025 - Present (6 months)
Built low-latency production voice AI pipelines with LiveKit, self-hosted ASR, LLM, and TTS, validating performance to 155 RPS for ASR and 56 RPS for TTS with p50 latency under 200 ms. Served Parakeet ASR and Kokoro TTS on L40S GPUs via Kubernetes, KubeRay, Ray Serve, and Docker, and reduced cold-start latency and timeouts by tuning async deployment and concurrency settings.
Machine Learning Intern
IHRD / SBCID Kerala
Mar 2023 - Dec 2023 (9 months)
Built an OCR pipeline to digitize and summarize local newspaper articles, reducing manual review time for analysts. Developed keyword extraction and article tagging for police case identification, improving classification accuracy by 20%, and created Indic-language translation and summarization workflows used by 20+ senior officials.
Education
Degrees, certifications, and relevant coursework
College of Engineering Kallooppara
Bachelor of Technology, Computer Science & Cyber Security
2022 - 2026
B.Tech in Computer Science and Cyber Security at College of Engineering, Kallooppara (Nov 2022–Apr 2026), with coursework completed and final results awaited. Dissertation covered fast fully homomorphic encryption via Module-LWE with parallel NTT algorithms, GPU roofline modeling, and IND-CPA security analysis.
Availability
Location
Authorized to work in
Job categories
Interested in hiring Rohith?
You can contact Rohith and 90k+ other talented remote workers on Himalayas.
Message RohithFind your dream job
Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!
