Open to opportunities

Charan Mogulla

@charanmogulla

Message

AI Engineer building production LLM agents and RAG systems with measurable accuracy, evals, and observability.

United States

Message

What I'm looking for

I’m looking to build reliable production LLM agents and RAG systems—partnering with stakeholders, instrumenting tracing/evals/observability, and continuously improving accuracy, latency, and cost.

I’m an AI Engineer with 3+ years architecting and shipping production LLM applications, agent-based systems, and RAG pipelines using LangChain. I’m comfortable engaging customers and stakeholders directly to translate business requirements into reliable AI architectures.

My work is grounded in measurable outcomes: I shipped a publicly live end-to-end AI agent (Checkmate) with LLM + RAG + evals + tracing + production deploy, driving a 40% accuracy lift and a 50% review-time reduction. I’ve also built AI services serving 100K+ users.

In my latest role, I productionized enterprise LLM applications with LangChain and OpenAI, improving contextual response accuracy by 40% and reducing hallucinations. I built multi-agent orchestration beyond single-call patterns, implemented LoRA/QLoRA fine-tuning pipelines, and established evaluation and feedback loops (prompt benchmarking and human-in-the-loop validation) to continuously raise quality and reliability.

Across projects, I emphasize end-to-end engineering: secure webhook/async processing, idempotent actions, retrieval quality, and production observability. I’ve used Langfuse and promptfoo for tracing, prompt versioning, and automated eval suites, and I enjoy building systems that are dependable in real deployment conditions.

Experience

Work history, roles, and key accomplishments

Current

AI Engineer

Current

Staffingtree.Inc

Aug 2023 - Present (2 years 10 months)

Architected and productionized enterprise LLM applications with LangChain and OpenAI, improving contextual response accuracy by 40% and reducing hallucinations. Built multi-agent orchestration, LoRA/QLoRA fine-tuning pipelines, and automated eval/observability loops; shipped a production LLM+RAG AI agent (Checkmate) serving 100K+ users and reducing review time by 50%.

LLMs (LangChain OpenAI Prompt Evaluation Docker CI CD

AI Engineer

Infosys

Jul 2022 - Jul 2023 (1 year)

Architected LLM-powered conversational AI systems with LangChain and Azure OpenAI on Azure App Services and AKS, supporting enterprise engagement platforms for 100K+ users. Implemented RAG with Azure Cognitive Search improving contextual accuracy by 35%, reducing hallucinations, and automating call-center resolution to cut average resolution time by 30%.

LLMs (LangChain Azure OpenAI RAG Azure Cognitive Search AKS Azure Services fastAPI Docker

Data Engineer

HCL Technologies

Dec 2020 - Jun 2022 (1 year 6 months)

Built and maintained scalable real-time data pipelines for enterprise logistics/transactions using Apache Kafka and Spark Streaming for fraud detection, improving detection accuracy and reducing response latency by 25%. Developed LLM-driven document summarization pipelines cutting manual review time by 50% and built containerized preprocessing and feature engineering workflows for downstream analy

Apache Kafka Data Pipelines SQL Postgres Fraud Detection Docker Feature Engineering

Education

Degrees, certifications, and relevant coursework

University of Central Missouri

Master of Science, Computer Science (AI & ML)

2023 - 2025

Grade: 3.6/4.0

Pursued a Master of Science in Computer Science (AI & ML), covering AI ethics, machine learning, NLP, deep learning, and data analytics. Earned a GPA of 3.6/4.0.