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

Generative AI and Machine Learning Engineer focused on shipping reliable, monitored, low-latency AI systems in production. I build retrieval-augmented generation (RAG) and agentic/multi-agent LLM workflows that are grounded, source-cited, and evaluated with offline quality and faithfulness metrics. I have nearly 4 years of experience orchestrating LLM applications with LangChain/LangGraph, implementing RAG retrieval and evaluation, and delivering production ML/LLMOps on AWS and Azure. I’m especially interested in turning deep-learning foundations (forecasting, anomaly detection) into practical, measurable impact for support and operations teams.…Generative AI and Machine Learning Engineer focused on shipping reliable, monitored, low-latency AI systems in production. I build retrieval-augmented generation (RAG) and agentic/multi-agent LLM workflows that are grounded, source-cited, and evaluated with offline quality and faithfulness metrics. I have nearly 4 years of experience orchestrating LLM applications with LangChain/LangGraph, implementing RAG retrieval and evaluation, and delivering production ML/LLMOps on AWS and Azure. I’m especially interested in turning deep-learning foundations (forecasting, anomaly detection) into practical, measurable impact for support and operations teams.

Charan Yalamakonda

AI Engineer, Data Scientist, Software Engineer, +1





Generative AI and Machine Learning Engineer focused on shipping reliable, monitored, low-latency AI systems in production. I build retrieval-augmented generation (RAG) and agentic/multi-agent LLM workflows that are grounded, source-cited, and evaluated with offline quality and faithfulness metrics. I have nearly 4 years of experience orchestrating LLM applications with LangChain/LangGraph, implementing RAG retrieval and evaluation, and delivering production ML/LLMOps on AWS and Azure. I’m especially interested in turning deep-learning foundations (forecasting, anomaly detection) into practical, measurable impact for support and operations teams.…Generative AI and Machine Learning Engineer focused on shipping reliable, monitored, low-latency AI systems in production. I build retrieval-augmented generation (RAG) and agentic/multi-agent LLM workflows that are grounded, source-cited, and evaluated with offline quality and faithfulness metrics. I have nearly 4 years of experience orchestrating LLM applications with LangChain/LangGraph, implementing RAG retrieval and evaluation, and delivering production ML/LLMOps on AWS and Azure. I’m especially interested in turning deep-learning foundations (forecasting, anomaly detection) into practical, measurable impact for support and operations teams.

Available to hire

Generative AI and Machine Learning Engineer focused on shipping reliable, monitored, low-latency AI systems in production. I build retrieval-augmented generation (RAG) and agentic/multi-agent LLM workflows that are grounded, source-cited, and evaluated with offline quality and faithfulness metrics.

I have nearly 4 years of experience orchestrating LLM applications with LangChain/LangGraph, implementing RAG retrieval and evaluation, and delivering production ML/LLMOps on AWS and Azure. I’m especially interested in turning deep-learning foundations (forecasting, anomaly detection) into practical, measurable impact for support and operations teams.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Work Experience

AI/ML Engineer at Uber

December 1, 2025 - Present

Built a production retrieval-augmented generation (RAG) pipeline over a ~30K-document internal knowledge base using FAISS dense retrieval with cross-encoder reranking. Replaced legacy keyword search to deliver grounded, source-cited answers for support and operations teams. Developed LangGraph multi-agent workflows with stateful message handling and tool calling to resolve multi-step operational queries, reducing manual back-and-forth. Implemented an offline evaluation harness measuring faithfulness and context precision/recall to catch grounding and retrieval regressions before release across ~2,000 daily queries. Containerized inference services with Docker on AWS EKS, serving retrieval under 300ms and reducing p95 response latency by 35% via Redis caching. Added guardrails and source-citation validation to curb ungrounded responses. Instrumented MLflow tracking and Prometheus monitoring across multiple drift and quality metrics to detect retrieval degradation in production.

Data Consultant – AI/ML at Dell Technologies

September 1, 2020 - August 1, 2023

Built churn and retention models using RNN and XGBoost on 120K+ customer records, improving early identification of at-risk accounts and raising churn-model F1 from ~0.64 to ~0.79. Engineered 25+ behavioral and temporal features using Python, SQL, and Pandas to strengthen model performance on sequential-learning tasks. Built PySpark and Apache Airflow ETL to process 2M+ records per cycle and consolidate data from 8+ business systems, reducing data-prep time and improving training consistency. Delivered prediction services via Flask and FastAPI, integrating six supervised models with CRM platforms and supporting 1K+ weekly requests with low-latency serving.