Headline

AI Engineer | Generative AI | LLMs | RAG Pipelines | AI Agents | NLP | Machine Learning | Python | FastAPI | AWS

About

I’m an AI Engineer specialized in fine-tuning, evaluating, and deploying LLMs (GPT, LLaMA, T5, BERT) using Hugging Face, PyTorch, and TensorFlow. I focus on building production-grade generative AI systems—not just prototypes—with reliability, scalability, and measurable business impact. I design agentic AI and RAG workflows using Model Context Protocol (MCP), LangGraph, CrewAI, and AutoGen to build multi-agent systems that can plan, call tools/APIs, maintain memory, and keep humans in the loop for critical decisions. On the multimodal side, I work with OpenAI, Gemini, Whisper, and other foundation models to ship AI experiences across text, speech, and code—delivered as real products, not experimental demos. Beyond modeling, I architect ML systems end-to-end: AWS SageMaker pipelines (data → training → HPO → deployment) Cloud-native architectures on AWS (EC2, Lambda, S3, CloudFormation) Automated evals, observability, and safety layers for LLMs & agents High-performance inference with vLLM, TGI, LoRA/QLoRA, AWQ/GGUF, caching, and custom embedding strategies I also build full-stack AI applications: FastAPI (Swagger/OpenAPI) backends, Streamlit/Tkinter frontends, Docker-based CI/CD, SQL/Postgres, and monitoring dashboards. My core strength: turning complex LLM and agentic AI capabilities into deployable, scalable systems that solve real business problems. If you’re building something meaningful in LLMs, agents, RAG, automation, or ML infrastructure, I’d love to connect.

Location

Greater Bengaluru Area

Work experience

AI Developer at Skills Agency, Jun 2026 - Present · 2 mos, Bengaluru, Karnataka, India, As an AI Developer, I work on AI/ML solutions, Generative AI, Large Language Models (LLMs), intelligent automation, and AI-powered applications. Throughout this journey, I have gained valuable knowledge and hands-on experience from my organization, working on real-world projects and business use cases. I have experience building MCP servers, AI bots, automation workflows, API integrations, and end-to-end AI solutions that help reduce manual effort, improve productivity, and streamline business operations. My work focuses on automating complete project workflows, enabling teams to work more efficiently and effectively. Additionally, I develop scalable backend services, work with databases such as MySQL and MongoDB, and build intelligent systems that integrate AI capabilities into practical business solutions. I am grateful for the opportunity to learn from experienced professionals, contribute to impactful projects, and continuously expand my knowledge in the fields of AI, automation, and intelligent systems. Looking forward to growing further, taking on new challenges, and making meaningful contributions in this exciting field.

AI Engineer & Researcher at Lancers Technology, Nov 2024 - Mar 2026 · 1 yr 5 mos, Bangalore Urban, Karnataka, India, As an AI Engineer, I worked on developing end-to-end intelligent systems across NLP, LLMs, RAG, automation, and multimodal AI. My role involved designing, training, and deploying machine-learning models, building production-ready AI workflows, and collaborating with cross-functional teams to integrate AI into real products. I contributed to multiple high-impact projects, including LLM fine-tuning, smart-contract auditing automation, social-media automation, and data-aggregation pipelines. Key Contributions & Responsibilities Built and fine-tuned multiple Large Language Models (GPT-4o, LLaMA, T5, BERT) for tasks like summarization, classification, data extraction, and content generation. Designed Retrieval-Augmented Generation (RAG) systems using vector databases, embeddings, and custom retrievers to enhance accuracy and reduce hallucinations. Developed AI agents and multi-agent workflows using LangChain, LlamaIndex, AutoGen, and OpenAI Assistants API, enabling tool-use, reasoning, and autonomous task execution. Created scalable ML pipelines and deployed AI services using FastAPI, Docker, AWS/GCP, n8n, Supabase, and CI/CD automation. Built intelligent automation tools and integrated GenAI models into real-world products and data-driven applications. Performed data preprocessing, prompt engineering, and model evaluation to optimize system performance and reliability.

Artificial Intelligence Internship at Pantech, Oct 2023 - Nov 2023 · 2 mos, Bengaluru, Karnataka, India, During my internship at Pantech Solution, I developed strong machine learning skills and gained hands-on experience in natural language processing tasks. My responsibilities included: Developing machine learning models for sentiment analysis and named entity recognition using frameworks like TensorFlow, PyTorch, and scikit-learn. Performing comprehensive data pre-processing, including cleaning, transforming, and preparing data for model training. Designing, implementing, and iterating on machine learning models to optimize their performance for the given tasks. Leveraging natural language processing techniques from the NLTK library to enhance the capabilities of the models. Analyzing model outputs, identifying areas for improvement, and making adjustments to the algorithms and architectures. Collaborating with the team to integrate the developed models into production systems and continually enhance their functionality.

Education

BCA, Computer Science, INDIAN ACADEMY GROUP OF INSTITUTIONS

Bi.P.C, Science, Sri Chaitanya College of Education