Autonomous Maritime AI: Designing and developing advanced AI capabilities for autonomous and uncrewed maritime platforms, including ALPV and USV-class vessels. Building LLM-powered systems for technical knowledge retrieval, structured reasoning, engineering decision support, and intelligent interaction with maritime data and internal systems. Applying Retrieval-Augmented Generation, tool-enabled workflows, prompt orchestration, evaluation frameworks, and safety controls to deliver reliable outputs in restricted and mission-critical environments.

Fuel Consumption Optimization: Developing optimization and machine learning models focused on reducing fuel consumption and improving operational efficiency across small, medium, and large maritime vessels. Formulating multi-objective optimization problems that account for vessel characteristics, propulsion behavior, operating profiles, route constraints, mission requirements, and changing environmental conditions. Building data processing and simulation workflows for telemetry analysis, feature engineering, scenario evaluation, model calibration, and performance validation.

Autonomous Vessel Decision Intelligence: Contributing to intelligent decision-support capabilities for autonomous maritime operations. Developing models that balance fuel efficiency, operational objectives, safety constraints, and platform-specific limitations. Designing solutions for integration with autonomous control systems and production maritime software, with emphasis on robustness, explainability, computational efficiency, and predictable behavior under complex operating conditions.

Production AI Engineering: Working across the full lifecycle of AI and optimization systems, from problem formulation and data engineering to experimentation, validation, deployment, and continuous performance assessment. Developing modular and production-ready solutions intended for high-reliability maritime applications where model quality, security, traceability, and operational resilience are critical.

Staffing Tool Search AI: Designed and implemented a microservices-based architecture (API, ETL, NLP) enabling hybrid employee search across structured and unstructured data. Built OpenSearch-based hybrid retrieval combining BM25 and dense vector search with alpha score fusion. Developed ETL pipelines generating vector and keyword indexes from PostgreSQL using transformer embeddings (all-MiniLM-L6-v2) with kNN similarity. Implemented an NLP layer with RAG and Gemini LLM for intent extraction and semantic understanding, deployed on AWS using Docker and Poetry. Automated with Jenkins.

PR Agent AI: Designed and deployed production-grade multi-agent AI systems supporting Procurement, Shipping, and Warehouse operations. Implemented RAG based agents for automated document processing, email handling, inventory updates, and decision support across enterprise systems. Built tool enabled agents integrated with internal APIs as MCP and infrastructure using advanced orchestration patterns (Prompt Chaining, Routing, Parallelization, Orchestrator-Worker). Developed solutions in Go using a custom DSL within an enterprise AI agent platform.

Material Cost AI Optimization: Architected and productionized ML/DL models (Ensemble, SVR, LSTM, GRU) for procurement price estimation and market forecasting. Integrated Explainable AI (SHAP, LIME) to ensure transparent and auditable decision support. Built scalable ETL pipelines ingesting supplier data into MongoDB and Snowflake, managed the full MLOps lifecycle with MLflow, Prometheus, and Grafana. Deployed containerized workloads on secure on-premise NVIDIA GPU infrastructure for high-performance training and inference.

Packaging Type Clustering Tool: Designed and deployed an AI-based classification system reducing 50+ packaging types to 5 standardized categories. Built semantic embedding pipelines using transformer models combined with clustering (K-Means, Hierarchical) and supervised classifiers (XGBoost, Logistic Regression). Integrated the solution with enterprise procurement systems and production inference pipelines. Ensured maintainability through modular architecture and automated retraining workflows.

MPN Forge Tool: Architected and deployed a hybrid retrieval system to resolve incomplete manufacturer part numbers with wildcards. Implemented multi-stage retrieval combining regex matching, fuzzy search (RapidFuzz), and semantic vector search using transformer embeddings. Developed XGBoost ranking models to prioritize candidates based on similarity and metadata features. Delivered scalable search APIs integrated into enterprise procurement workflows.

Forecasting Models: Designed and deployed AI-driven forecasting systems for material prices, stock availability, and supplier lead times. Implemented time-series models (XGBoost, LSTM, GRU) to capture trend, seasonality, and volatility. Built automated risk detection pipelines identifying price spikes, shortages, and supply disruptions. Integrated models into operational systems with continuous monitoring and retraining strategies.

Several ML and DL models: Delivered end-to-end ML/DL pipelines covering data collection, preprocessing, PCA, feature engineering, clustering (K-Means, GMM, Apriori), validation, and fine-tuning. Standardized experiment tracking, monitoring, and lifecycle management in MLflow. Implemented CI/CD workflows using Gitea and Azure for automated deployment and testing. Ensured reproducibility, scalability, and alignment with business objectives.

Pulse Platform Development: Designed and developed 16+ scalable Tableau dashboards delivering procurement and material flow insights across 100+ factories in 30+ countries. Built interactive reports with drill-down capabilities from global KPIs to granular operational data. Integrated multi-source pipelines from Snowflake, Oracle, MSSQL, PostgreSQL, and Teradata. Optimized data models and performance to support real-time analytics at global scale.

ETL and OLAP Pipelines: Designed and implemented 70+ ETL pipelines using Python and Alteryx to process 30TB+ of enterprise data. Developed batch and streaming ingestion frameworks with complex procurement and warehouse logic. Built OLAP models supporting analytical and reporting workloads. Optimized heterogeneous data integrations for performance, scalability, and production reliability.

Warehouse Optimization: Designed and deployed an AI-driven system to minimize picking time and maximize cart utilization. Modeled optimization using graph-based algorithms, clustering (K-Means), reinforcement learning, and Mixed-Integer Linear Programming. Built scalable Python pipelines integrated with warehouse management systems (WMS). Deployed real-time inference services improving operational efficiency and throughput.

Demand Forecasting: Designed and implemented time-series forecasting systems for customer order volumes and demand patterns. Applied XGBoost, Prophet, LSTM, and Temporal Fusion Transformer architectures to model trends and seasonality. Built Python ETL pipelines processing historical and streaming data stored in Snowflake. Delivered insights via Tableau dashboards and interactive Streamlit applications for business users.

Graph NN-Based Supply Chain Modelling: Designed and implemented a graph-based deep learning framework to model supply chain networks as dynamic graphs, representing suppliers, warehouses, distribution centers, and transportation routes as interconnected nodes and edges. Applied Graph Neural Networks (GNNs) to capture structural dependencies, propagation effects, and bottlenecks across the network. Integrated temporal components using hybrid GNN + LSTM architectures to model demand volatility, lead time variability, and disruption propagation. Deployed the model within production pipelines to support risk prediction, route optimization, and inventory balancing decisions at scale.

Quality Processes Automation: Developed Python automation tools streamlining quality workflows through rule-based document validation and concurrent processing. Reduced manual effort and improved document lifecycle efficiency. Optimized storage and operational processes, generating approximately $300K in annual savings. Deployed robust solutions with structured logging and exception handling in enterprise environments.

Managing Databases: Designed and implemented relational databases in MSSQL, Teradata, and Oracle for Engineering and Quality operations. Built optimized schemas, indexing strategies, and data models from scratch. Developed Python-based ETL integrations and refactored legacy structures for improved performance. Ensured data integrity, scalability, and consistency across enterprise systems.

SQA Management System: Designed and developed a multi-threaded Python desktop application managing blocked and incomplete deliveries in quality workflows. Built on a centralized Oracle transactional database supporting 40+ concurrent users. Implemented tracking and validation mechanisms improving shipment visibility and resolution efficiency. Delivered a stable, production-ready system adopted across quality teams.

Data Modelling: Developed high-performance SQL queries in MSSQL, Teradata, and Oracle using CTEs, window functions, and analytical aggregations. Extracted actionable insights from large-scale engineering and quality datasets. Optimized execution plans and indexing strategies for performance. Designed reusable data logic supporting reporting and root cause analysis.

Tableau Dashboards: Designed and delivered 12+ interactive dashboards enabling real-time KPI and defect monitoring for engineering, production and quality teams. Implemented drill-down analytics integrated with multiple enterprise data sources. Optimized performance for large-scale datasets. Supported data-driven decision-making across cross-functional stakeholders.

Focused on advanced computer science concepts, including distributed architectures, high-performance systems, and applied machine learning. Engaged in research-oriented coursework requiring formal analysis, experimentation, and technical validation. Applied mathematical modelling and system-level thinking to design robust, scalable solutions suitable for real-world deployment.

Acquired comprehensive technical foundations in software development and core computing principles, with emphasis on programming and system fundamentals. Completed multiple implementation-driven projects covering application development and database systems. Built practical engineering discipline through structured development processes, debugging, and collaborative project work.

Completed a formal technical education program focused on practical IT competencies, including computer systems administration, networking fundamentals, hardware configuration, and software installation. Developed hands-on expertise in diagnosing technical issues, configuring operating systems, and maintaining IT infrastructure. Successfully passed the national vocational examination with high distinction, earning the professional title of IT Technician.

Focused on architecting scalable, production-grade ML systems. Covered end-to-end pipeline design, infrastructure trade-offs, and reliability considerations. Emphasized latency, monitoring, and deployment best practices derived from large-scale industry environments.

Designed multi-agent architectures using LangGraph, CrewAI, and AutoGen. Implemented tool orchestration, task routing, and Docker-based deployments. Delivered complex agent collaboration systems including autonomous trading simulations.

Explored transformer architectures and post-GPT-3 LLM advancements. Analyzed architectural evolution and real-world NLP applications. Strengthened practical understanding of LLM deployment strategies.

Built responsive web applications using semantic HTML5 and modern CSS (Flexbox, Grid). Applied structured layout systems and UI/UX principles. Strengthened frontend debugging and optimization skills.

Implemented distributed MapReduce jobs in Python (MRJob) within the Hadoop ecosystem. Executed large-scale workloads locally and on AWS EMR. Applied NLP and analytical processing to real-world Big Data datasets.

Built advanced LLM systems using RAG, fine-tuning (QLoRA), and agent-based workflows. Developed multimodal and autonomous AI applications while benchmarking frontier and open-source models. Evaluated optimization strategies for production deployment.

Deployed LLM and multi-agent solutions across AWS, Azure, and GCP. Designed cloud-native architectures with CI/CD automation using Terraform and GitHub Actions. Integrated observability, guardrails, and Bedrock-based orchestration for enterprise-grade systems.

Completed Six Sigma Black Belt training focused on strategic DMAIC leadership and enterprise-level process optimization. Applied advanced statistical methods including Design of Experiments (DOE), multivariate regression, ANOVA, logistic modeling, and response surface methodology using Minitab. Utilized FMEA, control planning, and capability analysis to drive sustainable improvements in complex systems. Strengthened expertise in cross-functional transformation and data-driven performance governance.

Built semantic search systems using Weaviate and embedding pipelines. Designed vector schemas, optimized HNSW indexing, and deployed secure REST/gRPC APIs. Implemented hybrid retrieval strategies for improved search accuracy.

Covered Snowflake architecture, advanced SQL, and data pipeline design. Worked with structured and semi-structured data, including Streams and Time Travel. Integrated BI workflows and analytical best practices within modern data platforms.

Designed ETL workflows and predictive pipelines in Alteryx. Developed reusable macros and embedded scripting logic. Applied the platform in production-oriented analytics scenarios.

Earned certification validating advanced Tableau proficiency. Demonstrated expertise in data blending, multi-source integration, and dashboard design. Delivered business-focused visual analytics solutions.

Applied quantitative methods to supply chain segmentation and logistics optimization. Focused on forecasting, replenishment strategies, and risk management. Strengthened strategic supply chain decision-making skills.

Completed certified training in Six Sigma methodology with focus on the DMAIC framework (Define, Measure, Analyze, Improve, Control). Developed practical skills in statistical process control, hypothesis testing, regression analysis, and capability studies using Minitab. Strengthened expertise in root cause analysis, KPIV identification, and data-driven process optimization. 

Developed advanced SQL solutions including procedures, triggers, and access control. Focused on performance tuning and secure database administration. Strengthened relational data modeling skills.

Applied probability, statistics, and optimization models in supply chain contexts. Formulated data-driven solutions for logistics and inventory problems. Enhanced analytical rigor in operational decision-making.

Applied advanced visualization standards to improve dashboard clarity and usability. Translated stakeholder requirements into structured analytical layouts. Focused on audience-centered visual communication.

Strengthened Tableau fundamentals and data blending techniques. Emphasized analytical storytelling and structured visualization design. Delivered insight-driven visual outputs from complex datasets.