Currently working on GenAI and LLM projects, fine-tuning models, building AI agents, improving LLM evaluation, and exploring MLOps and AI infrastructure. π€
Iβm looking to collaborate on AI/ML and GenAI projects, open-source contributions, LLM applications, and practical AI systems. π€
Iβm looking for help with open-source contributions, advanced LLM engineering, model evaluation, and building reliable AI systems for production. π
Iβm currently learning LLM fine-tuning, agentic AI, LLM evaluation, MLOps, LLMOps, and production AI infrastructure. π§
Ask me about AI/ML, Generative AI, LLMs, RAG, AI agents, fine-tuning, MLOps, and building production-ready AI systems. π€
Fun fact: I enjoy turning complex AI ideas into working projects and then figuring out how to make them production-ready. π
-
π¨βπ» All of my projects are available at https://github.com/Abhijais4896
-
π I regularly write articles on https://dev.to/abhishekjaiswal_4896
-
π« How to reach me abhishek.77647@gmail.com
-
π Know about my experiences https://www.linkedin.com/in/abhishekjaiswal076
|
Dec 2025 β Jun 2026 Β· 06 months Worked on practical machine learning workflows involving exploratory data analysis, data cleaning, feature engineering, model development, and evaluation using real-world datasets. Focus:
|
Jun 2025 β Dec 2025 Β· 06 months Worked on machine learning workflows covering data preprocessing, feature engineering, model training, algorithm comparison, and performance evaluation. Focus:
|
|
Multimodal AI β’ LLM β’ Voice & Vision A multimodal AI healthcare assistant that combines vision, voice, and LLM capabilities to provide interactive AI-powered responses from text, speech, and image inputs. Stack: πΉ Vision-Language AI |
RAG β’ LLM Evaluation β’ LLMOps An enterprise-oriented RAG platform designed for reliable LLM applications with contextual retrieval, guardrails, evaluation, caching, and centralized LLM access. Stack: πΉ Retrieval-Augmented Generation |
|
Agentic AI β’ Multi-Agent Systems β’ LLM A multi-agent AI system where specialized agents collaborate to break down complex tasks, use external tools, and coordinate their results through structured workflows. Stack: πΉ Multi-Agent Orchestration |
LLM Fine-Tuning β’ LoRA β’ GPU Inference Fine-tuned an open-source LLM for natural-language-to-SQL generation using parameter-efficient fine-tuning, then deployed the model for GPU-based production inference. Stack: πΉ LoRA Fine-Tuning |
|
RAG β’ AI Research β’ LLM Applications An AI-powered investor intelligence platform that retrieves and synthesizes relevant company and financial information to support faster research and investment analysis. Stack: πΉ Intelligent Information Retrieval |
Machine Learning β’ MLOps β’ Model Lifecycle An end-to-end machine learning system for water potability prediction with reproducible training, dataset versioning, experiment tracking, and cloud-based deployment. Stack: πΉ Data & Model Versioning |


