Stanley (Chidera) Agwu-Senior AI Engineer | LLMs, RAG & Agent Systems
Check rate
Experience
Senior AI Engineer & Technical Lead
Independent / Freelance
- TrendReel, production LLM agent and RAG system (Python, LangChain, OpenAI, Groq/Llama 3, Claude, FastAPI, Kubernetes, PostgreSQL).
- Designed and built a production multi-step LLM agent system: a script generation agent with a per-platform psychology database, 7 viral narrative frameworks, and structured quality scoring, switching between Claude and Groq backends in real time based on output metrics.
- Implemented multi-provider LLM routing (Claude primary, Groq/Llama 3 fallback) with priority-chain failover and quality-based provider switching, achieving 95% inference cost reduction while holding measurable quality thresholds.
- Built an advanced RAG-style retrieval pipeline with per-platform knowledge bases, semantic content matching, and structured output evaluation across 7 decision frameworks, directly analogous to multi-tenant context-based reasoning for enterprise document workflows.
- BrainyAI, adaptive AI learning platform (Python, LangChain, Groq Llama 3.3-70B, OpenAI, Next.js, Supabase, Redis).
- Integrated Groq Llama 3.3-70B with education-level-aware prompting, dynamically adjusting vocabulary depth, citation complexity, and reasoning style across four student proficiency tiers.
- Nexus Prime, multi-tenant SaaS platform for marketing and growth automation (25 modules, 99 backend routers, 153 frontend files).
- Built a 25-module, 99-router multi-tenant SaaS platform covering ad remix, affiliates, WhatsApp inbox, email, and cart recovery, serving four subscription tiers from $199 to $1,999 per month with integrated Stripe, Paystack, and Flutterwave billing.
- AI Video Surveillance Platform, multi-tenant edge and cloud computer vision system currently in active client pitch.
- Designed a multi-tenant AI video surveillance platform combining edge YOLO26 inference on NVIDIA Jetson Orin NX boxes with a central GKE cloud layer (Postgres, Pub/Sub, ClickHouse, R2, Keycloak) for event storage, dashboards, alerting, and multi-tenancy.
Senior AI / Machine Learning Engineer
KoloXO
- Architected and delivered a unified scheduling and content automation platform supporting multi-brand, multi-tier operations (Basic, Premium, Enterprise), enabling seamless brand onboarding and management for scalable newsletter and social media campaigns.
- Engineered ETL pipelines and real-time data ingestion from 10+ heterogeneous sources at 95%+ data consistency, materially improving AI model reliability and downstream analytics.
- Deployed transformer-based NLP models (Google Gemini, custom LLMs) for content generation, cutting content creation time by 70% and enabling non-technical users to launch campaigns in minutes.
- Systematized end-to-end content scheduling, cross-platform publishing, and brand management workflows, eliminating over 8 hours per week of manual effort through intelligent automation.
Senior ML Engineer
Nabafat.AI
- Architected end-to-end MLOps infrastructure using Jenkins, Docker, Kubernetes, and Terraform, increasing deployment reliability by 40% and eliminating manual handoffs between development and production environments.
- Fine-tuned and deployed state-of-the-art LLMs (Mistral, Llama 3) on proprietary datasets, improving response relevance by 35% and reducing inference latency by 20% through systematic checkpoint benchmarking and optimized containerized serving.
- Designed and deployed a multi-LLM conversational AI assistant using LangChain, orchestrating multi-step reasoning, tool use, and context management to strengthen sales engineer interactions and lead capture efficiency in production.
- Built collaborative filtering recommendation pipelines that halved training time and increased recommendation precision by 20% through rigorous feature engineering and model evaluation.
- Implemented end-to-end experiment tracking and model lifecycle management with MLflow and ZenML, improving reproducibility by 50% through structured evaluation criteria, versioned artifacts, and full training-to-deployment traceability.
Computer Vision Engineer
Roc4Tech
- Developed and deployed YOLOv8 (weapon detection) and Mask R-CNN (instance segmentation) models for edge-deployed security drones, reaching mAP@0.5 of 0.94 with a 15% false negative reduction. Applied transfer learning (ResNet-50, VGG-16), lifting accuracy from 78% to 94% on a 50K-image dataset.
- Automated TensorFlow training and evaluation workflows on Azure, cutting training duration by 50% and boosting model performance by 20% through parallelized pipeline optimization.
Software Developer
Sentient LTD
- Engineered a real-time CNN drone surveillance system (25 FPS, 97% character recognition accuracy) and deployed ensemble fraud detection models, both operating as production systems with measurable operational impact.
- Built and deployed fraud detection models using ensemble classifiers, strengthening system security and measurably reducing fraud incidents in production.
Industry Experience
See where this freelancer has spent most of their professional time.
Experienced in Information Technology, Aerospace and Defense, Advertising, Education, and Retail.
Business Area Experience
See which departments and functions this freelancer has contributed to most.
Experienced in Information Technology, Product Development, Research and Development, and Marketing.
Summary
Senior AI Engineer with 5+ years of experience building and deploying production LLM systems, multi-agent architectures, and RAG pipelines end to end. Deep expertise in Python, LangChain, LlamaIndex, OpenAI APIs, multi-provider LLM orchestration, and agentic workflow design, with strong emphasis on reliability, evaluation, and responsible AI deployment. Delivered a 95% reduction in AI inference cost through intelligent multi-provider routing (Groq primary at $0.0005 per 1K tokens plus OpenAI fallback), a 70% reduction in content production time through automated agent pipelines, and a 35% improvement in LLM response relevance through systematic fine-tuning. Comfortable owning the full AI engineering lifecycle, from model selection and evaluation through production deployment and operational monitoring.
Skills
- Llm Agent Systems: Langchain (Advanced), Llamaindex, Multi-Agent Architecture, Agentic Workflow Design, Tool Use Orchestration, Multi-Step Reasoning, Context Management, Conversation History
- Rag & Retrieval: Rag Pipeline Design, Multi-Tenant Vector Store Architecture, Semantic Retrieval, Faiss, Pgvector, Context Window Optimization, Hybrid Search, Per-Platform Knowledge Bases
- Llm Fine-Tuning & Evaluation: Mistral, Llama 3, Gemini, Claude, Gpt-4, Fine-Tuning, Prompt Engineering, Benchmark Design, Evaluation Frameworks, Output Quality Scoring, Checkpoint Evaluation
- Inference & Serving: Multi-Provider Routing (Openai, Groq, Azure, Anthropic, Cartesia, Elevenlabs), Priority-Chain Failover, Inference Cost Optimization, Containerized Serving
- Generative Ai Frameworks: Hugging Face Transformers, Openai Api, Groq Api, Claude Api, Llamaindex, Haystack (Familiar), Embedding Models, Vector Databases
- Mlops & Infrastructure: Mlflow, Zenml, Kubernetes, Docker, Terraform, Prometheus/Grafana, Github Actions, Jenkins, Experiment Tracking, Model Versioning, Production Monitoring
- Cloud & Data: Gcp, Azure (Ml Studio, Speech, Ai Foundry), Aws (Sagemaker, Ec2), Fastapi, Postgresql (Async), Redis, Apache Kafka, Cloudflare R2
- Languages: Python (Advanced), Typescript/Javascript, Sql (Postgresql), Shell Scripting
Languages
Education
Enugu State University of Science and Technology
B.Eng. · Mechanical and Production Engineering · Nigeria
Certifications & licenses
Complete Machine Learning & Data Science Bootcamp
Artificial Intelligence & Machine Learning, Professional Certificate
Deep Learning with TensorFlow
Coursera
Practical Introduction to Machine Learning with Python
Statistics
Experience
Global Experience
Expertise
Qualifications
Profile
Frequently asked questions
Have questions? Find more information here.
Similar Freelancers
Discover other experts with similar qualifications and experience
Experts recently working on similar projects
Freelancers with hands-on experience in comparable project as a Senior AI Engineer & Technical Lead
