AI/ML Engineer with hands-on experience building LLM-powered and agentic systems for real-world applications. Skilled in Python, LangChain, RAG pipelines, vector databases (FAISS, Pinecone), and production-grade backend …
AI/ML Engineer with hands-on experience building LLM-powered and agentic systems for real-world applications. Skilled in Python, LangChain, RAG pipelines, vector databases (FAISS, Pinecone), and production-grade backend systems using FastAPI, Flask, and Docker. Experienced in LLM fine-tuning, prompt engineering, and scalable AI pipelines on AWS/GCP. Passionate about rapid prototyping, autonomous agent design, and mentoring peers in applied AI practices.
Developed and deployed RAG-based LLM pipelines with LangChain and vector databases, improving context accuracy and latency.
Developed asynchronous GPU-backed APIs for agentic workflows and real-time inference.
Mentored junior developers in best practices for deployment, CI/CD, and model versioning.
Rapidly prototyped AI features and iterative enhancements in a fast-paced environment, delivering production-ready solutions.
Integrated AWS Lambda and S3 for automation and scalability, reducing downtime by 25%, Optimized caching and website load times, enhancing customer engagement, Enhanced data security using modern encryption protocols and best practices
Developed Designed and deployed RAG-based LLM pipelines with LangChain and vector databases, improving context accuracy and latency., Developed asynchronous GPU-backed APIs for agentic workflows and real-time inference., Mentored junior developers in best practices for deployment, CI/CD, and model versioning., Rapidly prototyped AI features and iterative enhancements in a fast-paced environment, delivering production-ready solutions.
Automated AI workflows on AWS (Lambda, S3), improving system reliability and data uptime by 25%.
Enhanced model monitoring, caching, and AIOps mechanisms, reducing API latency by 20%.
Supported ETL pipelines and GPU-backed model inference systems for large-scale deployments.
Contributed to AI governance and compliance documentation for internal ML platform integration.
Automated AI workflows on AWS (Lambda, S3), improving system reliability and data uptime by 25%., Enhanced model monitoring, caching, and AIOps mechanisms, reducing API latency by 20%., Supported ETL pipelines and GPU-backed model inference systems for large-scale deployments., Contributed to AI governance and compliance documentation for internal ML platform integration.
Built and deployed high-accuracy (95%) ML models using Python, TensorFlow, and scikit-learn, Designed and optimized data pipelines with advanced preprocessing, boosting model accuracy by 25%, Conducted model performance profiling using TensorBoard, improving inference speed by 20%, Deployed models using Flask APIs and collaborated with full-stack developers for seamless integration, Explored use of LangChain and RAG pipelines for document-based question answering
The AI-first Recruitment Operating System that unifies and automates the entire hiring lifecycle for modern enterprises worldwide.
Dr Job FZ LLC. 2026 © All Rights Reserved
