Logistics Route Planning Engine With Traffic and Weather Awareness

Added Jun 2025 3 design docs

For logistics operators, routing is a daily optimization problem with real money attached: traffic, weather, delivery windows, and fuel costs shift constantly, and a plan that was optimal at six in the morning is stale by nine. Dispatchers need routes that adapt, and finance teams need the cost story behind every plan they approve.

The intern builds a route planning platform where generative AI produces and revises delivery plans. Given a fleet, a set of stops, and live constraints such as traffic conditions, weather, vehicle capacity, and driver hours, the AI generates route plans with sequencing rationale and cost analyses, then regenerates them as conditions change. A Node.js backend manages plan generation and real-time updates, MongoDB stores fleets, routes, and revision history, and the React frontend presents interactive maps where dispatchers inspect, adjust, and approve routes before exporting driver schedules. Secure user management keeps operator, dispatcher, and driver views appropriately distinct.

The project blends optimization thinking with modern AI tooling and teaches the intern to build software where generated plans must survive contact with real-world constraints and human oversight.

Related projects

End-to-End Encrypted Messaging System for Clinical Teams

Clinical teams routinely discuss patients over channels never designed for medical confidentiality, and every unencrypted message is a liability for the organization and a risk to the patient. This project builds a messaging platform where privacy is enforced by cryptography rather than policy. The intern implements AES-based end-to-end encryption so messages are readable only by their intended participants, never by the server that relays them. Password storage uses salting and key derivation functions, session and authentication management follow hardened practices, and the intern implements core cryptographic algorithms directly to understand what libraries usually hide. A brute-force attack simulation module demonstrates concretely why the chosen parameters resist real adversaries. The stack combines a Node.js backend, MongoDB persistence, Python tooling for the cryptographic and attack-simulation components, and a React interface for the messaging experience. The project turns abstract security concepts into implemented, testable code. The intern finishes able to explain and defend an end-to-end encryption design, a rare and credible skill for security-focused roles in healthcare technology and beyond.

healthcaretechnologycryptographycybersecuritymongodb+4

PRD · HLD · LLD includedView

TechnologyMedium

Knowledge Retrieval Service for Energy Sector Documents on Vertex AI

Energy companies manage some of the densest documentation in industry: grid compliance filings, environmental impact assessments, turbine maintenance manuals, and regulatory correspondence spanning decades. Engineers and analysts lose hours locating provisions inside these archives, and institutional knowledge walks out the door with every retirement. A retrieval system that answers plain-language questions from this corpus, hosted on infrastructure the company already trusts, addresses both problems at once. The intern builds this knowledge retrieval service as a cloud-based application on Google Cloud's Vertex AI. Documents are processed and embedded into a vector index, and a Python pipeline built with LangChain performs retrieval-augmented generation: fetching the passages relevant to a query and composing answers through OpenAI and Vertex AI models with citations back to the source documents. The intern implements the document processing workflow, the retrieval configuration tuned for long technical documents, and the query API through which analysts interact with the system, all deployed and running on GCP services. The project demonstrates cloud-native AI engineering: building RAG on a managed ML platform, handling industrial document collections, and delivering grounded question answering with the citation discipline that regulated sectors require.

energygcpgenerative-ailangchain+2

PRD · HLD · LLD includedView

TechnologyHard

Pest Detection From Field Images With AI Treatment Guidance

Crop pests can erase a season's profit in weeks, and by the time damage is visible from the road, treatment options have narrowed and costs have multiplied. Smallholders and agronomists alike need early detection that works from ordinary field photos combined with the sensor data farms already collect. The intern builds an IoT-enabled detection platform in Python. Field images are analyzed with OpenCV to isolate leaves and lesions, and generative AI identifies likely pests, produces treatment recommendations in plain language, and drafts scouting reports for agricultural stakeholders. Real-time IoT sensor data covering humidity, temperature, and leaf wetness enriches the analysis, since outbreak risk depends as much on conditions as on sightings. MongoDB stores images, detections, and sensor streams, powering outbreak tracking maps and visual analytics that show how infestations spread across fields over time, with secure user management and exportable reports completing the product. The intern learns to fuse computer vision, sensor telemetry, and generative AI into one decision-support pipeline, and to present uncertain model output in a way a farmer can act on responsibly.

agricultureresearchgenerative-aiiotmongodb+2

PRD · HLD · LLD includedView