Yogendra A
@yogendraa
I build production-ready AI/ML systems with fast, efficient inference.
IndiaWhat I'm looking for
At L&T Technology Services, I helped redesign concurrent ML inference pipelines, reducing end-to-end latency by 98%, model footprint by 83%, and CPU utilization by 60%.
I've built end-to-end AI products including VoiceRAG, a FastAPI and FAISS knowledge assistant with Whisper transcription and SSE streaming, and a CNN-LSTM pranayama analysis system that achieved 78.4% test accuracy. I also work across AsyncIO, WebSockets, AWS, GCP, databases, and production backend integration.
Experience
Work history, roles, and key accomplishments
Assisted in designing and developing machine learning algorithms for concurrent ML inference workloads, reducing end-to-end latency by 98% through pipeline redesign. Contributed to integrating AI models into production systems, reducing model footprint by 83% and CPU utilization by 60%.
Education
Degrees, certifications, and relevant coursework
PES University
Bachelor of Technology, Computer Science and Engineering
2022 - 2026
Pursuing a Bachelor of Technology in Computer Science and Engineering.
Availability
Location
IndiaAuthorized to work in
ZimbabwePortfolio
github.com/Yogendra-AJob categories
Skills
Interested in hiring Yogendra?
You can contact Yogendra and 90k+ other talented remote workers on Himalayas.
Message YogendraGet matched with your dream remote job
Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!
