Hire Abdul Samad - AI Engineer

* Develop AI and Generative AI solutions using Python, LLMs, RAG, and AI agents. * Build and integrate intelligent applications using LangChain, LangGraph, vector databases, and modern LLM frameworks. * Develop scalable AI services and APIs using FastAPI and Python. * Work on NLP, machine learning, deep learning, and production-oriented AI solutions. * Collaborate with cross-functional teams to design and deliver AI-powered business solutions.

As an AI Engineer at C10 AI LLP (A Helios Core AI LLC Company), I specialize in designing, developing, and deploying AI-powered intelligent agents and AI-driven solutions to solve real-world business challenges. My role involves building conversational AI agents, integrating Large Language Models (LLMs), and implementing end-to-end AI pipelines using technologies like Python, TensorFlow, PyTorch, and OpenAI APIs. I have hands-on experience in developing Retrieval-Augmented Generation (RAG) based agents, automating business processes, and integrating AI systems with REST APIs. I actively work on deploying AI models securely and efficiently on cloud platforms such as AWS, GCP, and Azure, leveraging Docker, Kubernetes, and CI/CD pipelines. I am passionate about optimizing AI workflows for scalable and production-ready deployments while focusing on model accuracy, latency reduction, and security. My expertise also extends to vector databases, data pre-processing, and implementing AI agents for web search, text-to-speech, and image generation tasks. I am committed to continuously learning and contributing to AI-powered automation, enabling businesses to simplify operations and elevate their decision-making capabilities through cutting-edge AI solutions.

As an Associate AI Engineer at Tap Health, I designed and deployed an AI-driven medical diagnosis system, integrating Agentic AI to enhance scalability and efficiency in healthcare diagnostics. I developed multi-agent architectures with CrewAI for collaborative decision-making among virtual AI doctors, knowledge retrievers, and medical assistants, while leveraging Neo4j for structured, graph-based medical insights to improve diagnostic accuracy. Additionally, I built Retrieval-Augmented Generation (RAG) pipelines to provide real-time access to relevant medical literature, reducing misdiagnosis rates. I implemented secure role-based authentication and session management for clinical settings and utilized LangChain and OpenAI models for symptom-based AI reasoning. To optimize system performance, I integrated asynchronous task handling using Redis Queue (RQ), enabling real-time medical report generation with minimal latency.