Nanditha S

Nanditha S

Generative AI Field Solutions Architect
Chennai , Tamil Nadu , India
Tamil, English, Malayalam

نبذة عني

GenAI Engineer with 1+ year of experience designing and deploying production-ready generative AI systems across computer vision, audio, and LLM-powered applications. Proficient in Python, PyTorch, LangChain, OpenCV, Fast…

الخبرة

GenAI Engineer

Eros Innovation - Immerso.ai, Chennai, Tamil Nadu
Feb 2025 - حتى الآن · 1 سنة 8 أشهر

<p>Architected 3 production GenAI services (LLM APIs, computer vision pipelines) handling 1,000+ daily requests at 99.5% uptime<br>
Reduced API latency by 40% via async execution and intelligent model caching across REST endpoints<br>
Cut manual ML effort by 60% by automating preprocessing, augmentation, and validation pipelines end-to-end<br>
Accelerated model inference 3x with ONNX Runtime and CUDA tuning; reduced GPU memory usage by 50%<br>
Managed 10,000+ monthly file transactions using PostgreSQL for metadata and AWS S3 for media storage</p>

GenAI Engineer

Eros Innovation - Immerso.ai, Chennai, Tamil Nadu · Chennai , Tamil Nadu , India
Jan 2025 - حتى الآن · 1 سنة 9 أشهر

<p>Architected 3 production GenAI services (LLM APIs, computer vision pipelines) handling 1,000+ daily requests at 99.5% uptime, Reduced API latency by 40% via async execution and intelligent model caching across REST endpoints, Cut manual ML effort by 60% by automating preprocessing, augmentation, and validation pipelines end-to-end, Accelerated model inference 3x with ONNX Runtime and CUDA tuning; reduced GPU memory usage by 50%, Managed 10,000+ monthly file transactions using PostgreSQL for metadata and AWS S3 for media storage</p>

المهارات

لينكس بوستجريس كيو إل بايثون (لغة برمجة) نمذجة البيانات فلاسك (إطار عمل لتطبيقات الويب باستخدام Python) كيراس نومباي (مكتبة لغة Python) تينسور فلو دوكر SQL LangChain LlamaIndex Prompt Engineering Retrieval-Augmented Generation (RAG) LLM Fine-Tuning LoRA Instruction Tuning Agents Chain-of-Thought Multimodal AI LLM Deployment Semantic Retrieval Vector Embeddings Scalable AI Systems Real-Time AI Processing OpenAI GPT Llama Mistral HuggingFace Transformers PyTorch ONNX Runtime vLLM Triton Inference Server Whisper CUDA Acceleration GPU Acceleration FAISS Pinecone ChromaDB Weaviate Semantic Search Embedding Models Scikit-learn Pandas Random Forest XGBoost SVM Regression Clustering FastAPI REST APIs Async Processing gRPC Background Job Processing AI Pipelines SQLAlchemy AWS S3 Git CUDA VS Code Jupyter PyCharm
الإبلاغ عن هذا الملف الشخصي؟