AI/ML Engineer - GenAI, RAG, Production ML

Praveen Beeneedi AI/ML Engineer

CT, USA +1-475-***-**** *******.*****@*****.*** LinkedIn

SUMMARY

AI/ML Engineer with 5+ years of experience designing and deploying enterprise AI, machine learning, and Generative AI solutions using Python, SQL, LLMs, RAG, NLP, and cloud-native technologies. Experienced in building intelligent search, AI assistants, recommendation systems, and scalable ML applications using LangChain, FastAPI, Docker, Kubernetes, and AWS, with a strong focus on automation, production reliability, and enterprise knowledge management. Proven ability to optimize AI performance, streamline ML workflows, and deliver secure, scalable solutions that improve operational efficiency and business decision-making.

TECHNICAL SKILLS

Programming Languages: Python, SQL, Java, JavaScript, Bash Machine Learning: Scikit-learn, TensorFlow, PyTorch, XGBoost, Classification, Regression, Clustering, Recommendation Systems, Feature Engineering, Hyperparameter Tuning, Model Evaluation, Model Validation

Generative AI: OpenAI API, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Prompt Engineering, LangChain, LlamaIndex, AI Agents, AI Assistants, Semantic Search, Embeddings, Vector Databases

Natural Language Processing: Text Classification, Sentiment Analysis, Named Entity Recognition (NER), Entity Extraction, OCR, Document Summarization, Keyword Extraction Frameworks & APIs: FastAPI, Flask, REST APIs, Microservices MLOps & Deployment: Docker, Kubernetes, Apache Airflow, CI/CD, ML Pipelines, Model Monitoring, Inference Pipelines, Experiment Tracking, Production Deployment Cloud Platforms: AWS (EC2, S3, Lambda, SageMaker), Azure, Google Cloud Platform (GCP) Databases & Vector Stores: PostgreSQL, MySQL, MongoDB, Redis, Pinecone, FAISS, ChromaDB Data Engineering: Pandas, NumPy, ETL Pipelines, Data Cleaning, Data Validation, Workflow Automation, Batch Processing, SQL Analytics

Visualization & Reporting: Power BI, Tableau, KPI Dashboards, Executive Reporting, Data Visualization Tools & Practices: Git, GitHub, Linux, Jira, Agile, SDLC, Cross-Functional Collaboration, Technical Documentation, Version Control

PROFESSIONAL EXPERIENCE

AI/ML Engineer Aug 2023 – Present CT, USA

Cisco Systems

• Designed and deployed enterprise RAG applications using LLMs, LangChain, embeddings, and vector databases, improving knowledge search accuracy by 42% across internal engineering and operations teams.

• Developed AI-powered assistants using Python, FastAPI, and REST APIs to automate knowledge retrieval, technical support, and workflow automation, reducing manual support effort by 38%.

• Improved response quality and reduced inference costs by 22% through prompt engineering, context optimization, semantic retrieval, and response caching strategies.

• Built automated evaluation pipelines to validate hallucination, groundedness, latency, and response consistency before production deployments, improving reliability of enterprise AI applications.

• Developed intelligent document-processing pipelines using OCR, document summarization, classification, and entity extraction, reducing document review time from hours to minutes.

• Deployed scalable AI inference services using Docker, Kubernetes, and cloud-native deployment practices, maintaining 99.9% application availability across production environments.

• Designed secure FastAPI microservices and REST APIs to integrate semantic search, document intelligence, and AI capabilities into enterprise applications, accelerating product delivery by 30%.

• Automated machine learning workflows using Apache Airflow, implementing scheduled training, inference, monitoring, and retry mechanisms that reduced manual engineering effort by 45%.

• Enhanced recommendation models using user behavior analytics and ranking optimization techniques, increasing user engagement and click-through rates by 27%.

• Partnered with Product, Security, Data Engineering, and Platform teams to deliver secure, scalable AI solutions while reducing release timelines by 25% through standardized deployment and governance practices.

Machine Learning Engineer May 2020 - Aug 2022 India Mphasis

• Improved campaign targeting accuracy 24% by building churn prediction, fraud detection, and segmentation models using Python, SQL, and Scikit-learn across enterprise customer datasets.

• Raised model precision 24% through feature engineering, hyperparameter tuning, class balancing, and structured validation across high-volume structured production data environments.

• Reduced manual text review 35% by creating NLP pipelines for sentiment scoring, classification, and entity extraction from customer interaction records.

• Cut batch runtime 40% by automating ETL workflows using Python, SQL scheduling, and data quality checks supporting downstream analytics teams.

• Reduced decision turnaround 33% by deploying Flask APIs serving real-time predictions into operational systems and customer-facing business workflows daily.

• Improved leadership visibility 30% by building Power BI dashboards tracking KPIs, forecasts, trends, and model performance across business units.

• Lowered incident impact 28% by implementing anomaly detection models that surfaced failures earlier and improved operational response speed.

• Reduced infrastructure costs 20% by optimizing compute scheduling, training workloads, and environment utilization across concurrent machine learning initiatives.

• Increased deployment success 26% by partnering with analysts and engineers to productionize scalable machine learning workflows across cloud platforms.

• Strengthened audit readiness by maintaining version control, lifecycle documentation, reproducible runs, and standardized handoff practices across engineering teams. EDUCATION

Master of Science in Computer Science Aug 2022 - Apr 2024 CT, USA University of Bridgeport at Bridgeport

Bachelor of Engineering in Computer Science & Engineering Aug 2017-May 2021 India Gitam University

Contact this candidate