Dzaky Alfitra
Generative AI EngineerAI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Generative AI Engineer with 1+ years in LLM Applications & AI Agent Development
Electrical Engineering student and AI/ML engineer focused on building and deploying generative AI applications. Experienced in developing LLM-based conversational agents with LangChain and the OpenAI SDK, self-hosting and serving open-source LLMs and vision-language models (VLMs) for real research use cases, and integrating AI models into FastAPI and Streamlit based applications. Background in deep learning research (PyTorch, computer vision) provides a strong foundation in AI/ML fundamentals, data pipelines, and model evaluation. Comfortable working across the AI stack, from prompt engineering and API orchestration to deployment on local GPU servers and edge devices.
SYIAH KUALA UNIVERSITY
Bachelor · Electrical Engineering
August 1, 2022 – Present
Syiah Kuala University
AI Researcher of Coffee Bean Grading System
August 1, 2025 – Present
Banda Aceh, Aceh, Indonesia
KROENG (Community of Robotics & Electrical Engineering)
Vice Leader
February 1, 2024 – February 1, 2025
Banda Aceh, Aceh, Indonesia
Syiah Kuala University
Electronic Laboratory Assistant
September 1, 2023 – Present
Banda Aceh, Aceh, Indonesia
Jeski, Conversational AI Assistant
January 1, 2026 – Present
Built a context-aware chatbot using LangChain and the OpenAI SDK, with a custom memory system supporting multi-turn conversations. Designed and iterated on prompts to shape assistant behavior, tone, and response quality. Deployed the assistant through a self-hosted, publicly accessible web interface.
Self-Hosted LocateAnything (Vision-Language Model)
January 1, 2026 – Present
Deployed NVIDIA's LocateAnything VLM on a local RTX 6000 Ada GPU server. Built a Streamlit interface for remote, cross-device access over a public network. Gained hands-on experience with GPU server infrastructure and API/package routing for serving large AI models without cloud dependency.
Self-Hosted MedGemma (Medical LLM)
January 1, 2026 – Present
Deployed Google's MedGemma 1.5 locally using Ollama and OpenWebUI to analyze medical images such as skin lesions, MRI/CT inputs. Served a research team's skin-analysis workflow without relying on cloud infrastructure, demonstrating practical, cost-efficient deployment of open-source medical LLMs.
Face Recognition Attendance System
January 1, 2026 – Present
Led AI integration: deployed and connected a face-recognition model to cloud infrastructure and microcontroller hardware. Achieved 98% recognition accuracy under proper lighting conditions, with an average processing time of 3 seconds.
Two additional papers on Mosaic Packed Augmentation and the Coffee Grading System
Unknown
June 1, 2026 – Present
Comparative Study of Object Detection Models for Dense Coffee Bean Defect Detection Using YOLOv11, Faster R-CNN, and RetinaNet. Accepted - AIMS 2025, AJT Press.
AIMS (AJT Press)
January 1, 2025 – Present
Achieved 76% on the Data Scientist — Artificial Intelligence test, demonstrating a solid grasp of core AI/ML principles, though with room for improvement in specific areas.
Strengths
Limitations
Cultural Fit Analysis
The candidate's profile shows a strong inclination towards self-initiated projects and research, indicating a proactive and curious mindset. Their involvement in a robotics and engineering community and as a lab assistant suggests a collaborative spirit and willingness to contribute to a team environment. The diversity of projects, from conversational AI to medical LLMs and object detection, demonstrates a broad interest in AI applications. The target role of Generative AI Engineer aligns well with their project experience in LLM applications and VLM deployment.
Soft Skills & Operational Fit
The candidate's experience as a Vice Leader and Electronic Laboratory Assistant suggests leadership potential, organizational skills, and the ability to guide and mentor others. Their self-initiated projects demonstrate strong initiative and problem-solving capabilities. The psychometric test score of 294/500 (58.8%) suggests average logical reasoning, work attitude, stress handling, and team collaboration, which could be an area for development.
Scored 88% on the Python Internship Test, indicating a very strong command of Python programming, including algorithms, data analysis, and testing.
Strengths
Limitations