Ramesh Yadav Nalagarla

Ramesh Yadav Nalagarla

+•• ••••• •••••••••••@•••••.com

Machine Learning Engineer · ASICS Technologies Pvt Ltd · 7.2 yrs

As a Machine Learning Engineer, I am driven by a logical and pragmatic approach to problem-solving, consistently seeking mastery and taking full accountability for delivering robust, intelligent systems. My ambition fuels my autonomous pursuit of innovative solutions in AI and data engineering, ensuring precision and efficiency in every project.

  • Hyderabad
  • Open to Hyderabad
  • Hybrid, Remote

Ask about Ramesh

Skills

Claimed

Multi-Agent System IntegrationRetrieval-Augmented GenerationLarge Language Model ConceptsSpark SQLGoogle Cloud PlatformProduct DevelopmentTelecommunications Industry KnowledgeHealthcare Domain KnowledgeFintech Domain KnowledgeBanking Product KnowledgeListening AttentivelySpeaking Clearly

Proof of Experience

Machine Learning Engineer

ASICS Technologies Pvt Ltd · Sep 2023 – Present

  • Developed machine learning models using XGBoost, Random Forest, Isolation Forest, and Autoencoders for fraud detection and anomaly detection.
  • Built scalable end-to-end ML pipelines for data ingestion, preprocessing, model training, evaluation, deployment, and monitoring.
  • Processed over 150 million healthcare claim records using PySpark and Databricks.
  • Implemented advanced feature engineering and anomaly scoring techniques to identify suspicious claims.
  • Developed real-time fraud scoring APIs using Flask and FastAPI.
  • Deployed machine learning models using Azure Machine Learning and Vertex AI.
  • Implemented MLOps workflows using MLflow, Docker, Kubernetes, Terraform, and GitHub Actions.
  • Built automated CI/CD pipelines for machine learning deployment.
  • Designed Power BI dashboards for fraud analytics and business reporting.
  • Implemented model monitoring, drift detection, logging, and alerting mechanisms.
  • Improved fraud detection accuracy by 27%.
  • Reduced false positive alerts by 22%.
  • Designed and developed Generative AI applications using Python, FastAPI, and Large Language Models (LLMs).
  • Built Retrieval-Augmented Generation (RAG) pipelines using LangChain/LangGraph with vector databases for enterprise knowledge retrieval.
  • Integrated LLM APIs such as OpenAI, Azure OpenAI, and Anthropic Claude into AI applications.
  • Developed AI agents with tool calling, memory management, and multi-step reasoning using LangGraph and AutoGen.
  • Created document Q&A chatbots by processing PDFs, Word, Excel, and web content using embedding models.
  • Implemented prompt engineering techniques to improve response accuracy, consistency, and reduce hallucinations.
  • Used vector databases such as Pinecone, FAISS, ChromaDB, or Azure AI Search for semantic search and retrieval.
  • Built REST APIs using FastAPI to expose AI services for frontend and third-party integrations.
  • Implemented conversation memory, session management, and chat history for personalized AI assistants.

DevOps&Mlops

Asics Technologies · Nov 2019 – Feb 2026

  • Built end-to-end MLOps pipelines for automated model training, validation, deployment, and monitoring.
  • Deployed machine learning models as REST APIs using FastAPI and Flask, containerized with Docker, and orchestrated using Kubernetes.
  • Automated CI/CD pipelines using GitHub Actions, Jenkins, and Azure DevOps for seamless model deployment.
  • Managed model versioning, experiment tracking, and artifact management using MLflow.
  • Deployed models on AWS SageMaker, Azure Machine Learning, and Google Vertex AI.
  • Implemented blue-green and rolling deployment strategies to achieve zero-downtime model releases.
  • Built real-time inference services capable of handling high-volume prediction requests with auto-scaling.
  • Monitored model performance using Prometheus, Grafana, and cloud-native monitoring tools.
  • Implemented data drift, concept drift, and model performance monitoring to maintain prediction accuracy.
  • Configured automated alerts for latency, throughput, CPU, memory utilization, and model accuracy degradation.
  • Developed automated retraining pipelines triggered by model drift and performance thresholds.
  • Logged prediction requests, model outputs, and inference metrics for auditing and troubleshooting.
  • Optimized inference latency and resource utilization through Kubernetes autoscaling and model optimization.
  • Integrated feature pipelines with model serving to ensure consistent training and inference data.
  • Improved deployment reliability by implementing automated testing, rollback mechanisms, and health checks.

Cloud Engineer

Previous Organization · Sep 2021 – Aug 2023

  • Designed and managed AWS cloud infrastructure for enterprise banking applications.
  • Implemented Infrastructure as Code using Terraform and CloudFormation.
  • Automated application deployments using Jenkins, GitHub Actions, and AWS CodePipeline.
  • Managed containerized applications using Docker and Kubernetes (EKS).
  • Configured AWS services including EC2, S3, RDS, Lambda, IAM, API Gateway, and CloudWatch.
  • Implemented blue-green and rolling deployment strategies.
  • Developed monitoring and alerting solutions using Prometheus, Grafana, and CloudWatch.
  • Improved system availability, scalability, and deployment efficiency.
  • Collaborated with development teams for release management and production support.

Cloud Engineer

Previous Organization · Sep 2019 – Aug 2021

  • Led migration of telecom applications from on-premises infrastructure to AWS cloud.
  • Automated cloud infrastructure provisioning using Terraform.
  • Built CI/CD pipelines for automated application deployment.
  • Managed Docker containers and Kubernetes clusters.
  • Configured monitoring, logging, and alerting solutions using Prometheus, Grafana, and CloudWatch.
  • Implemented disaster recovery and backup solutions.
  • Optimized cloud resource utilization and reduced infrastructure costs.
  • Managed IAM roles, VPC networking, security groups, and compliance policies.
  • Supported production environments with high availability and scalability requirements.
  • Automated operational tasks using Shell Scripting and Python.

Proof-of-Work

No completed sessions yet. Anything Ramesh finishes shows up here with the evidence behind it.

Proof of Education

Bachelor of Technology

JNTU Anantapur

A Proof CV — one profile, kept current, with the proof attached. Back to the portal