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

Hello, I’m Rohini Swathi Bhatlapenumarthi, a GenAI Engineer with 8+ years of experience architecting LLM-based solutions, RAG pipelines, and multi-agent systems across AWS Bedrock, Amazon Q Business, and GCP Vertex AI. I design, fine-tune, and deploy transformer models that accelerate enterprise decision-making, reduce latency, and uphold ethical AI governance. I bridge AI research and DevOps to deliver scalable, secure, and highly available GenAI platforms. I collaborate with cross-functional teams—data science, risk, and compliance—to productionize responsible GenAI solutions, build observability into inference pipelines, and design governance that aligns with regulatory frameworks. I’m passionate about turning cutting-edge research into practical, reliable AI systems that empower organizations to innovate with confidence.…Hello, I’m Rohini Swathi Bhatlapenumarthi, a GenAI Engineer with 8+ years of experience architecting LLM-based solutions, RAG pipelines, and multi-agent systems across AWS Bedrock, Amazon Q Business, and GCP Vertex AI. I design, fine-tune, and deploy transformer models that accelerate enterprise decision-making, reduce latency, and uphold ethical AI governance. I bridge AI research and DevOps to deliver scalable, secure, and highly available GenAI platforms. I collaborate with cross-functional teams—data science, risk, and compliance—to productionize responsible GenAI solutions, build observability into inference pipelines, and design governance that aligns with regulatory frameworks. I’m passionate about turning cutting-edge research into practical, reliable AI systems that empower organizations to innovate with confidence.

Rohini Swathi Bhatlapenumarthi

AI Engineer, AI Developer, Data Scientist, +2





Hello, I’m Rohini Swathi Bhatlapenumarthi, a GenAI Engineer with 8+ years of experience architecting LLM-based solutions, RAG pipelines, and multi-agent systems across AWS Bedrock, Amazon Q Business, and GCP Vertex AI. I design, fine-tune, and deploy transformer models that accelerate enterprise decision-making, reduce latency, and uphold ethical AI governance. I bridge AI research and DevOps to deliver scalable, secure, and highly available GenAI platforms. I collaborate with cross-functional teams—data science, risk, and compliance—to productionize responsible GenAI solutions, build observability into inference pipelines, and design governance that aligns with regulatory frameworks. I’m passionate about turning cutting-edge research into practical, reliable AI systems that empower organizations to innovate with confidence.…Hello, I’m Rohini Swathi Bhatlapenumarthi, a GenAI Engineer with 8+ years of experience architecting LLM-based solutions, RAG pipelines, and multi-agent systems across AWS Bedrock, Amazon Q Business, and GCP Vertex AI. I design, fine-tune, and deploy transformer models that accelerate enterprise decision-making, reduce latency, and uphold ethical AI governance. I bridge AI research and DevOps to deliver scalable, secure, and highly available GenAI platforms. I collaborate with cross-functional teams—data science, risk, and compliance—to productionize responsible GenAI solutions, build observability into inference pipelines, and design governance that aligns with regulatory frameworks. I’m passionate about turning cutting-edge research into practical, reliable AI systems that empower organizations to innovate with confidence.

Available to hire

Hello, I’m Rohini Swathi Bhatlapenumarthi, a GenAI Engineer with 8+ years of experience architecting LLM-based solutions, RAG pipelines, and multi-agent systems across AWS Bedrock, Amazon Q Business, and GCP Vertex AI. I design, fine-tune, and deploy transformer models that accelerate enterprise decision-making, reduce latency, and uphold ethical AI governance. I bridge AI research and DevOps to deliver scalable, secure, and highly available GenAI platforms.

I collaborate with cross-functional teams—data science, risk, and compliance—to productionize responsible GenAI solutions, build observability into inference pipelines, and design governance that aligns with regulatory frameworks. I’m passionate about turning cutting-edge research into practical, reliable AI systems that empower organizations to innovate with confidence.

Skills

Experience Level

Expert

Expert

Expert

Expert

Work Experience

GenAI Engineer / AI Engineer at Fannie Mae

October 1, 2024 - November 11, 2025

Architected a GenAI Forms Recommendation Engine using LangChain and retrieval-augmented generation on AWS Bedrock, improving retrieval accuracy by 65% and reducing manual classification time from hours to minutes. Integrated Amazon Q Business APIs to enable enterprise-level document search and conversational insights, boosting internal compliance productivity by 40%. Designed a multi-agent orchestration framework with LangGraph and Bedrock embeddings to automate legal document summarization across 50K+ records, delivering 40% faster turnaround. Deployed fine-tuning workflows with LoRA/QLoRA on Bedrock and Databricks Mosaic AI, achieving 25% lower latency and 18% higher contextual accuracy. Implemented real-time prompt evaluation and reinforcement scoring to monitor safety and trust alignment, cutting false positives by 30%. Built an end-to-end LLMOps pipeline with MLflow, Docker, and Kubernetes to support zero-downtime retraining and versioned deployments across AWS regions. Establishe

Generative AI Engineer / AI & ML Engineer at Delta Dental

September 30, 2024 - September 30, 2024

Developed an enterprise-grade ChatGPT assistant integrated with RAG plus Vertex AI and Bedrock, reducing average customer-service response time by 20% and improving first-contact resolution by 15%. Engineered a self-learning knowledge bot using LangChain + FAISS with 0.93 semantic similarity accuracy and real-time query expansion for 300+ agents. Orchestrated GenAI pipelines on GCP Dataflow + Apache Beam, reducing data-processing latency by 35% and enabling daily model refresh cycles for 20M records. Integrated Amazon Q Business and Vertex AI for hybrid search + reasoning, increasing answer precision by 25% in multi-document retrieval. Automated model training and deployment via Airflow + BigQuery ML + Azure ML with 99.9% uptime SLO. Implemented prompt-optimization and feedback loops reducing hallucinations by 22%. Implemented vector indexing and retrieval QA with FAISS and LangChain achieving 95% KB coverage; Designed multi-cloud deployment (Azure + GCP) for fault-tolerance and GDPR c

DevOps / Cloud Automation Engineer at Mercedes-Benz

July 31, 2023 - July 31, 2023

Engineered CI/CD pipelines with Jenkins + Terraform + Azure DevOps, automating build and deployment for 50+ microservices and reducing release cycles by 45%. Automated cloud infrastructure provisioning for hybrid Azure + AWS environments with IaC templates. Introduced containerization of ML services with Docker and Kubernetes to standardize model training and deployment. Optimized endpoint management with Intune + SCCM for 5K+ devices, improving provisioning speed by 30% and reducing manual errors by 80%. Implemented Grafana dashboards and CloudWatch alerts to monitor infra usage and reliability. Developed self-healing Python scripts to auto-remediate bottlenecks, increasing uptime by 25%. Standardized IaC blueprints and DevOps SOPs for AI/data automation pipelines. Worked with AI & Data Science teams to provision GPU-enabled VM clusters, cutting environment setup time from days to hours. Enhanced VDI performance to support ML workloads and improve developer productivity by 20%.Mentore

DevOps Engineer at Barclays

April 30, 2021 - April 30, 2021

Automated Linux patching and provisioning with Ansible/Bash, saving 15 engineer-hours per week. Streamlined infrastructure provisioning across 200+ Linux servers with Ansible + Terraform, cutting manual maintenance time by 70%. Built CI/CD pipelines with Jenkins and GitHub Actions for reproducible deployments. Developed Python-based health-check and remediation scripts, reducing outages and improving SLA adherence to 99.8%. Integrated AWS CloudWatch and Prometheus for real-time visibility and improved proactive alerting. Optimized PostgreSQL/MySQL automation and near-instant schema deployment, speeding up test cycles by 40%. Established IaC standards to support future ML infra automation. Collaborated with security to harden configurations and implement zero-trust policies. Built observability and telemetry frameworks forming the foundation for MLOps adoption. Reduced release rollback frequency by 35% via automated validation checks.