Backend Engineer

Open to full-time

Bio

Nornubari J. is a Backend Engineer with over 5 years of experience in designing and developing high-performance, fault-tolerant applications in AI and software engineering. He is proficient in Python, FastAPI, and Flask for backend development, and utilizes Apache Kafka, Apache Spark, and Apache Airflow for creating robust data pipelines. Nornubari employs CI/CD practices with tools like Terraform, Jenkins, and Docker, and has expertise in managing databases such as MongoDB, PostgreSQL, and Redis. His work often involves integrating machine learning models using frameworks like Keras, PyTorch, and TensorFlow. At CONANO SYSTEMS, Nornubari led the development of an AI assistant for farmers, achieving a 20% increase in crop yields through effective pest control solutions. At Peggy Labs, he reduced school onboarding costs by over 90% through a multi-agent extraction system and achieved 98% accuracy in data extraction for school logistics. Nornubari holds a B.Eng. in Chemical Engineering from the Federal University of Technology, Owerri. He is well-suited for roles focusing on AI-driven backend development and scalable application design.

Expertise

PythonFlaskMongoDBKafkaPySparkKubernetesCSSHTMLTypeScriptAWSTerraformJenkinsFast APIDocument DatabaseDatabase CachingRelational DatabaseSQLPyTorchFlutterGit

Video Intro

Assessments

General Coding Assessment

Perfect score on LRU Cache Question, Difficulty Medium · Great score on Two Algorithm Questions, Difficulty Medium

Projects

Farmpest Copilot API

This is a farm pest control AI assistant. It utilizes deep learning to detect farm pests and LLM to recommend control measures. Farmers take a photo of the pest on their farm, and the app identifies and recommends control measures to the farmer. This will help increase crop yields for farmers and curb the harmful effects of climate change.

Research Copilot API

Research Copilot is application that help researchers gain more insight into their work while saving time and cost.

Authentication and Authorization API

This is a highly secured API based authentication and authorization service that authenticates client requests to the server, implementing rotational refresh tokens for access token renewals.

Errand

This is an e-commerce event driven microservice application with the aim of providing a highly available, scalable, and secured e-commerce experience on multiple devices.

Spyke

This is a social media application that incorporates e-commerce features.

Peggy

AI parenting school logistics App that turns chaotic school emails into structured todo cards. It has auto archive irrelevant emails, reminders, add to calendar, morning and evening daily digests, etc features.

Experience

AI Software Engineer
CONANO SYSTEMS· AI/MLFeb 2020 — Jun 2024
- I collaborated with 3 cross-functional teams to ideate and develop an AI assistant for farmers to help control pest and diseases. This resulted in 20% crop yield for farmers.
- I achieved 97% model and evaluation accuracies during the training pest image classification model on 187,858 dataset containing images of plan pest and diseases using Keras
- Reduced trained model deployment time to production by 70% using MLFlow, Dagshub and DVC
- Collaborated with 3 cross-functional teams to design and develop a highly secured and resilient Authentication Service that made use of token rotation and DPoP.
- Maintained latency below 200ms under heavy production workload using SWR, Event-driven architecture, strict clean architecture, CQRS, etc
- Led 3 cross-functional teams to design and develop an e-commerce mobile application API endpoints using FastAPI.
PythonAWSApache KafkaMachine LearningFastAPIRedisKubernetes
Agentic AI Engineer
Peggy Labs· AI/MLJun 2024 — May 2026
- Reduced school onboarding cost from ~$2 to ~$0.11 per school by designing a multi-agent extraction system with cost-optimized LLM routing across GPT-4o-mini, Grok 4-fast, DeepSeek, and Gemini 2.5 Flash, replacing what would have been hours of manual data entry per provider.
- Cut redundant processing costs from $1 to ~$0.03 by building a resource deduplication layer that allowed agents to reuse scraped or downloaded documents from other agents, eliminating double-fetching across the pipeline.
- Achieved 98% extraction accuracy across school details, divisions, grades, schedules, leads, and district data using intelligent model fallback strategies and structured output validation with PydanticAI
- Implemented a hybrid scraping stack combining Scrapfly and Browserbase CDP via Playwright, maximizing extraction success (about 98%) across anti-bot-protected and JavaScript-heavy school websites.
- Built a reusable agent framework with dependency injection and multi-provider LLM support, enabling rapid development of new extraction agents and reducing agent development time by 70% across the team.
- *Evals:* Validated extraction quality at ~95% accuracy using Braintrust with LLM-as-judge scoring against a golden dataset of 400 US schools, ensuring production reliability before rollout.
- Reduced kids school public calendar events import cost from ~$1.50 to ~$0.20 per school by architecting a multi-agent pipeline that automatically extracts closures, early dismissals, and notable days — eliminating manual calendar entry for thousands of schools.
- Handled 6 distinct school calendar source types (interactive JavaScript calendars with multi-month Playwright navigation, static HTML pages, PDF documents, images via OCR, Google Docs, and ICS feeds), maximizing coverage of 99% across diverse school websites.
- Leveraged the shared resource deduplication layer to reuse previously scraped content across ingestion and calendar agents, further reducing per-school processing cost and latency.
- Automated end-to-end calendar delivery by persisting extracted events and exporting them to per-child Google secondary calendars with grade-specific filtering, directly reducing parent workload by 90%.
- *Evals:* Achieved ~97% extraction accuracy validated via Braintrust with LLM-as-judge scoring against a golden dataset of 200 US schools across all calendar source types.
- Achieved 40% improvement in user experience by integrating iOS Live Activities for real-time email ingestion progress tracking using Firebase Cloud Messaging (FCM) v1 API, giving parents instant visibility into processing status.
- 60% increase in parent engagement by developing scheduled morning and evening digest system delivering personalized event summaries via SMS (Twilio) and WhatsApp (Bird), keeping parents informed without requiring them to open the app.
- Reduced school discovery latency by 85% by building a gRPC-based search API with zipcode-to-coordinates geocoding, dynamic radius management, and grid-based spatial caching, delivering sub-second search results for parents finding nearby schools.
PythonDjangoFastAPIAWSBraintrustPydanticPydanticAILogfireSentryDatadogLLMAgents