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

Hi, I'm Lahari Gurram, an AI Engineer specializing in designing and deploying production-grade machine learning and generative AI solutions using Python, PyTorch, TensorFlow, and LangChain. I enjoy turning complex data into practical, scalable AI applications that empower teams and stakeholders. I have built retrieval-augmented generation pipelines, fine-tuned LLMs (GPT-4, Claude, Gemini), and developed multi-agent workflows to automate processes while improving response quality. I prioritize observability, secure PII-compliant deployments, and close collaboration with cross-functional teams to deliver scalable GenAI solutions on Azure and cloud platforms.…Hi, I'm Lahari Gurram, an AI Engineer specializing in designing and deploying production-grade machine learning and generative AI solutions using Python, PyTorch, TensorFlow, and LangChain. I enjoy turning complex data into practical, scalable AI applications that empower teams and stakeholders. I have built retrieval-augmented generation pipelines, fine-tuned LLMs (GPT-4, Claude, Gemini), and developed multi-agent workflows to automate processes while improving response quality. I prioritize observability, secure PII-compliant deployments, and close collaboration with cross-functional teams to deliver scalable GenAI solutions on Azure and cloud platforms.

Lahari Gurram

AI Engineer, Data Scientist, Web Developer, +3





Hi, I'm Lahari Gurram, an AI Engineer specializing in designing and deploying production-grade machine learning and generative AI solutions using Python, PyTorch, TensorFlow, and LangChain. I enjoy turning complex data into practical, scalable AI applications that empower teams and stakeholders. I have built retrieval-augmented generation pipelines, fine-tuned LLMs (GPT-4, Claude, Gemini), and developed multi-agent workflows to automate processes while improving response quality. I prioritize observability, secure PII-compliant deployments, and close collaboration with cross-functional teams to deliver scalable GenAI solutions on Azure and cloud platforms.…Hi, I'm Lahari Gurram, an AI Engineer specializing in designing and deploying production-grade machine learning and generative AI solutions using Python, PyTorch, TensorFlow, and LangChain. I enjoy turning complex data into practical, scalable AI applications that empower teams and stakeholders. I have built retrieval-augmented generation pipelines, fine-tuned LLMs (GPT-4, Claude, Gemini), and developed multi-agent workflows to automate processes while improving response quality. I prioritize observability, secure PII-compliant deployments, and close collaboration with cross-functional teams to deliver scalable GenAI solutions on Azure and cloud platforms.

Available to hire

Hi, I’m Lahari Gurram, an AI Engineer specializing in designing and deploying production-grade machine learning and generative AI solutions using Python, PyTorch, TensorFlow, and LangChain. I enjoy turning complex data into practical, scalable AI applications that empower teams and stakeholders.
I have built retrieval-augmented generation pipelines, fine-tuned LLMs (GPT-4, Claude, Gemini), and developed multi-agent workflows to automate processes while improving response quality. I prioritize observability, secure PII-compliant deployments, and close collaboration with cross-functional teams to deliver scalable GenAI solutions on Azure and cloud platforms.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Work Experience

Gen AI Engineer at Kadence

August 1, 2024 - Present

Designed and deployed enterprise-grade Generative AI solutions using LLMs (GPT-4, Claude, Gemini), automating workflows and improving operational efficiency. Developed Retrieval-Augmented Generation (RAG) pipelines with LlamaIndex and vector databases (Pinecone, Weaviate, Milvus, Chroma), improving response relevance by 20% and reducing hallucinations. Engineered prompt strategies, function-calling schemas, and tool integrations, increasing LLM response accuracy across production use cases. Integrated GenAI services with backend systems using Python, Node.js, and REST APIs, scaling to high daily request volumes with stable uptime. Implemented LLM evaluation, observability, and monitoring using LangSmith, Weights & Biases, and Prometheus/Grafana, reducing production regressions by 18%. Fine-tuned and optimized LLMs, embedding models, and rerankers using LoRA/QLoRA/PEFT, reducing inference latency while preserving model quality. Deployed and managed self-hosted open-source LLMs and ML pi

AI Engineer – AI/ML Platform at Grid Dynamics

May 1, 2022 - June 1, 2023

Developed and deployed ML models for classification, regression, and clustering using scikit-learn, XGBoost, and LightGBM; improved prediction accuracy for enterprise datasets by 20%. Performed feature engineering, data cleaning, and preprocessing; evaluated models using precision, recall, F1-score, and ROC-AUC. Built NLP solutions including sentiment analysis, named entity recognition (NER), and text classification using pre-trained embeddings (Word2Vec, GloVe, FastText) and Hugging Face Transformers. Fine-tuned BERT and smaller transformer models for domain-specific text tasks using PyTorch and Hugging Face; improved NLP model relevance. Designed and maintained ML data pipelines using Pandas and SQL for structured and semi-structured datasets; streamlined preprocessing for training and inference by 25%. Assisted in model deployment in dev/test environments with Docker and cloud ML services. Collaborated with cross-functional teams to integrate ML/NLP models into applications, ensurin