Home

Sameer Alluri - SENIOR AI ENGINEER

[email protected]

Location: Chicago, Illinois, USA

Relocation: YES

Visa: GC

Resume file: Sameer Chaitanya Alluri Resume_1772563580395.docx Please check the file(s) for viruses. Files are checked manually and then made available for download.

Senior AI Engineer with over 12 years of experience in developing and deploying machine learning solutions across healthcare, marketing, and financial services. Proven track record of leveraging data science and AI to drive business value such as reducing hospital readmissions, boosting customer engagement, and optimizing risk models. Hands-on expertise in Python, TensorFlow, scikit-learn, and NLP (Hugging Face Transformers), with extensive experience deploying models on AWS (SageMaker, Lambda, etc.) and optimizing end-to-end ML pipelines. Adept at MLOps best practices, model deployment, and cross-functional collaboration, with a passion for translating complex data problems into impactful AI solutions. Experienced in integrating Google Cloud LLMs and building search pipelines using Google Vector Search and hybrid search methodologies. Proven track record of collaborating with data scientists, data engineers, and DevOps teams to build and deploy ML models using AWS SageMaker in hybrid environments. Skilled in SageMaker Pipelines, model monitoring, fine-tuning LLMs, and implementing CI/CD workflows for robust MLOps solutions. Designed and implemented Retrieval-Augmented Generation (RAG) pipelines using Azure OpenAI, Azure AI Search, and Python, enabling natural language querying over enterprise datasets Integrated Azure OpenAI GPT models with Azure AI Search to retrieve contextual information and generate accurate, grounded responses. Developed orchestration workflows using LangChain and Semantic Kernel for document retrieval, embedding generation, and LLM response generation. Built scalable backend services using Python (FastAPI) to expose REST APIs for AI-powered applications Extensive experience designing and deploying enterprise conversational AI solutions using LangGraph and Dialogflow CX, enabling multi-agent orchestration, stateful workflows, and intelligent automation Designed and implemented AI-powered SRE automation agents for incident detection, root cause analysis (RCA), and automated remediation using Amazon Bedrock and Claude LLM. Integrated Amazon Bedrock (Claude) for log summarization, anomaly detection, intelligent alert correlation, and automated postmortem generation. Built AI-driven observability pipelines integrating CloudWatch, Prometheus, and Grafana for proactive incident monitoring and MTTR reduction. Developed self-healing infrastructure workflows using Python and AWS Lambda to auto-remediate failed services in EKS environments. Implemented runbook automation using LLM-powered agents with LangChain for intelligent change impact analysis and infrastructure troubleshooting. Deployed Kubernetes (EKS) production workloads with Infrastructure-as-Code using Terraform and AWS CloudFormation. Proficient in Explainable AI (XAI) and production-ready LLM customization for agentic systems. Strong hands-on knowledge in Python, PyTorch, TensorFlow, Keras, and NLP frameworks like SpaCy, NLTK, Hugging Face Transformers. Deep implementation experience in GPT, LLaMA, Claude, BERT, RoBERTa, and LangChain, with expertise in Vector Databases, LoRA, RAG, PEFT, and Knowledge Graphs. Well-versed in AWS cloud ecosystem (SageMaker, EC2, Lambda, EMR, S3) with strong experience in Jupyter Notebooks, agentic programming, and building AI solutions such as GraphRAG, Chain of Thought (CoT), and Tree of Thought (ToT). Deep expertise in Amazon Bedrock (FMs, embeddings, Guardrails), RAG architectures, hybrid retrieval, and enterprise LLM deployment. Keywords: continuous integration continuous deployment artificial intelligence machine learning sthree