Cesar Sanchez-Coronel

Also known as Carlos Cesar Sanchez Coronel (Carlos César Sánchez Coronel).

AI Engineer · Data Engineer · AI Infrastructure & Operations

Agentic AI · Data Platforms · Production AI Ops

Industrial & Enterprise AI

Lima, Peru · UTC-5

Industrial & Enterprise AI

Open to remote & relocation · English B2 · Spanish native

Lima, Peru 🇵🇪 · UTC-5

I take LLM systems from prototype to production — designing multi-agent architectures (LangGraph, RAG) over a terabyte-scale Azure Databricks Lakehouse at BCP.
Six+ years in energy, mining, and industrial operations (Enel, Abengoa, Orica, On Energy) before moving into data and AI; I've walked the plants my models optimize.
I work where domain context matters — not just models in a notebook.

Energy
Mining
Telecommunications
Consumer goods
Banking

Selected Work

Multi-Agent Analytics for a Banking Lakehouse

Enterprise · Banking · In production

Multi-agent system (LangGraph + RAG over Azure Databricks) that automates metadata lineage exploration across a terabyte-scale Lakehouse at BCP.

Repository →

AI-Driven Data Lineage & Metadata Auditing

GenAI · Data Governance

LLM pipeline that parses legacy stored procedures and maps dependency graphs (Python + NetworkX) to automate lineage auditing.

Repository →

Autonomous Multi-Agent System for Edge Computing

Edge AI · Robotics · MSc Research

Hardware-constrained multi-agent stack for industrial edge processing over real-time sensor telemetry, Docker-optimized inference.

Repository →

Experience

  1. Dec 2025 — Present

    Senior Data & AI Specialist · BCP (banking, via Indra)

    Lead AI initiatives on the bank-wide Azure Databricks Lakehouse: multi-agent systems (LangGraph, RAG), terabyte-scale metadata engineering, AI governance with enterprise stakeholders.

  2. Jan 2025 — Dec 2025

    Data & AI Engineer · Gloria (consumer goods, Peru)

    Pricing & revenue-growth ML models (Microsoft Fabric), LLM-based automation for manual data processing, end-to-end PySpark pipelines across Azure, AWS, and on-prem.

  3. Apr 2024 — Dec 2024

    IT Analytics Engineer · WIN (telecom / ISP)

    Distributed telemetry pipelines (PySpark, Airflow, Kafka), metadata engineering, churn prediction models, and conversational SQL-agent prototypes over OpenAI APIs.

  4. Feb 2022 — Mar 2024

    Data Engineer · Secram Ingenieros (industrial engineering)

    Built the company's first Data Warehouse (T-SQL, SSIS), Python RPA for legacy data extraction, and Power BI reporting for operations.

  5. 2014 — 2021

    Energy & Mining (Enel · Abengoa · Orica · On Energy)

    Techno-economic analytics for battery storage and power markets, predictive maintenance data, SCADA telemetry — the industrial foundation behind my AI work today.

Stack

Agentic AI & LLMs

Focus: LLM-based and multi-agent systems in production — RAG pipelines and agentic workflows.

  • Stack: LLMs, RAG, Multi-Agent Systems, LangGraph, LangChain, Hugging Face, OpenAI API, FastAPI, PyTorch, Scikit-learn.

Data Engineering & Platforms

Focus: Lakehouse architectures, ETL/ELT pipelines, metadata management, and terabyte-scale data platforms.

  • Stack: Azure, AWS, Databricks, Microsoft Fabric, PySpark, Airflow, Kafka, Delta Lake, Python, SQL (T-SQL), PostgreSQL, Power BI.

Edge, Infrastructure & AI Ops

Focus: MLOps, cloud-native deployment, edge inference, and production observability.

  • Stack: Docker, Kubernetes, NVIDIA, GPU Inference, Linux, Terraform, MLflow, Grafana, GitHub Actions, CI/CD.

Research & Teaching

🔬 Research

M.Sc. in Artificial Intelligence, Universidad Nacional de Ingeniería. Thesis: Hybrid Edge-Cloud Routing for SLMs in Edge AI: Empirical Evaluation of Latency, Cost, and Resilience.

AI & Data Track

🧱 Foundations & Computing

⚙️ Machine Learning & Systems

🧠 Deep Learning Track

Generative AI Applications