Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I’m an Applied AI Engineer with 6+ years of experience building production ML and LLM systems for enterprise products. I’ve used LangChain, RAG, Spark, and TensorFlow to automate real-time support and document workflows—cutting ticket resolution time by 60%, improving invoice processing to 98% accuracy, and reducing annotation costs by 40% through better data pipelines and active learning. I enjoy taking systems from prototype to reliable deployment: monitoring and evaluation (drift detection, A/B testing), standardized model serving patterns, and scalable MLOps practices with CI/CD and observability. Most recently, I’ve been building multi-agent LangChain workflows and self-updating knowledge systems that detect knowledge base drift and continuously improve performance, and I’m excited to grow further into architecting robust multi-agent platforms and end-to-end MLOps pipelines.…I’m an Applied AI Engineer with 6+ years of experience building production ML and LLM systems for enterprise products. I’ve used LangChain, RAG, Spark, and TensorFlow to automate real-time support and document workflows—cutting ticket resolution time by 60%, improving invoice processing to 98% accuracy, and reducing annotation costs by 40% through better data pipelines and active learning. I enjoy taking systems from prototype to reliable deployment: monitoring and evaluation (drift detection, A/B testing), standardized model serving patterns, and scalable MLOps practices with CI/CD and observability. Most recently, I’ve been building multi-agent LangChain workflows and self-updating knowledge systems that detect knowledge base drift and continuously improve performance, and I’m excited to grow further into architecting robust multi-agent platforms and end-to-end MLOps pipelines.

Damian De La Cerda

AI Engineer, Data Scientist, Software Engineer, +4





I’m an Applied AI Engineer with 6+ years of experience building production ML and LLM systems for enterprise products. I’ve used LangChain, RAG, Spark, and TensorFlow to automate real-time support and document workflows—cutting ticket resolution time by 60%, improving invoice processing to 98% accuracy, and reducing annotation costs by 40% through better data pipelines and active learning. I enjoy taking systems from prototype to reliable deployment: monitoring and evaluation (drift detection, A/B testing), standardized model serving patterns, and scalable MLOps practices with CI/CD and observability. Most recently, I’ve been building multi-agent LangChain workflows and self-updating knowledge systems that detect knowledge base drift and continuously improve performance, and I’m excited to grow further into architecting robust multi-agent platforms and end-to-end MLOps pipelines.…I’m an Applied AI Engineer with 6+ years of experience building production ML and LLM systems for enterprise products. I’ve used LangChain, RAG, Spark, and TensorFlow to automate real-time support and document workflows—cutting ticket resolution time by 60%, improving invoice processing to 98% accuracy, and reducing annotation costs by 40% through better data pipelines and active learning. I enjoy taking systems from prototype to reliable deployment: monitoring and evaluation (drift detection, A/B testing), standardized model serving patterns, and scalable MLOps practices with CI/CD and observability. Most recently, I’ve been building multi-agent LangChain workflows and self-updating knowledge systems that detect knowledge base drift and continuously improve performance, and I’m excited to grow further into architecting robust multi-agent platforms and end-to-end MLOps pipelines.

Available to hire

I’m an Applied AI Engineer with 6+ years of experience building production ML and LLM systems for enterprise products. I’ve used LangChain, RAG, Spark, and TensorFlow to automate real-time support and document workflows—cutting ticket resolution time by 60%, improving invoice processing to 98% accuracy, and reducing annotation costs by 40% through better data pipelines and active learning.

I enjoy taking systems from prototype to reliable deployment: monitoring and evaluation (drift detection, A/B testing), standardized model serving patterns, and scalable MLOps practices with CI/CD and observability. Most recently, I’ve been building multi-agent LangChain workflows and self-updating knowledge systems that detect knowledge base drift and continuously improve performance, and I’m excited to grow further into architecting robust multi-agent platforms and end-to-end MLOps pipelines.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Language

Javanese

Advanced

Work Experience

AI Engineer at Forethought

August 1, 2024 - Present

Developed LangChain multi-agent workflows with prompt engineering and reasoning plus API integrations (payment gateways, CRM) to automate real-time support actions, cutting ticket closure time by 60% and manual work by 40%. Built a self-updating ML system using vector embeddings to detect knowledge base drift and auto-merge resolved insights, improving accuracy by 25% (human-evaluated precision) and reducing onboarding time for new agents. Replaced legacy RAG/evaluation frameworks with AIMon monitoring, drift detection, and A/B testing while standardizing model serving patterns to improve LLM output accuracy on code-inclusive queries to 95%. Architected a low-code platform using Docker containerization and pluggable data source adapters to deploy AI agents across diverse SaaS products in under 2 weeks, increasing customer satisfaction by 30%. Implemented semantic search with a vector database to aggregate multi-source data, reducing issue investigation time from 90 to under 50 minutes

Machine Learning Engineer at Tally

August 1, 2023 - July 1, 2024

Built AI predictive analytics models on transaction data using scikit-learn, TensorFlow, and time-series methods, achieving 85% forecast accuracy and 30% fewer errors. Engineered an intelligent document processing (IDP) pipeline with OpenCV OCR and fine-tuned BERT via REST APIs to automate invoice scanning with 98% accuracy and 90% automation, saving 200+ manual hours monthly. Orchestrated real-time streaming pipelines using Kafka/Kinesis and Spark Structured Streaming for feature engineering (including sentiment analysis) in recommendation systems processing 500k+ events/hour. Implemented ML-powered QA bug detection models on AWS SageMaker to accelerate testing cycles by 35% and enable earlier issue prediction. Deployed anomaly detection systems to flag data entry discrepancies, reducing compliance violations by 28% and improving data accuracy.

Software Development Engineer – AI/ML at Amazon

January 1, 2021 - July 1, 2023

Improved reliability of production ML by implementing data validation and drift detection and model monitoring pipelines using Python, MLflow, and Great Expectations within CI/CD workflows, reducing performance degradation and increasing system stability by 15%. Architected scalable recommendation system pipelines using collaborative filtering, feature engineering, and personalization logic, achieving an 8% lift in simulated user engagement. Designed data labeling and active learning workflows for document processing, integrating a feature store and model registry and exporting curated datasets to BigQuery—reducing annotation costs by 40% and improving NLP training data quality. Enhanced real-time inference infrastructure by optimizing model serving (TensorFlow Serving) and deployment pipelines with Kubernetes autoscaling and GPU acceleration, reducing latency by 30% and compute costs. Built data pipeline optimization for text processing using Apache Spark, Airflow, and Kafka streami