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

I’m an AI Infrastructure Engineer with 9+ years of experience building distributed systems, production APIs, and managed cloud platforms that power reliable AI features. Over the last 3+ years, I’ve led GenAI/LLM infrastructure initiatives focused on observability, evaluation, and safe integration patterns across AWS, Azure, and GCP. I build end-to-end systems for agentic workflows and RAG—designing MCP servers/clients, integrating Azure OpenAI and AWS Bedrock (including the Claude model family), and implementing monitoring for latency/throughput, drift, and quality degradation. I enjoy turning complex requirements into well-instrumented, secure, and scalable services using Python, FastAPI, Kubernetes, Terraform, and strong API lifecycle practices.…I’m an AI Infrastructure Engineer with 9+ years of experience building distributed systems, production APIs, and managed cloud platforms that power reliable AI features. Over the last 3+ years, I’ve led GenAI/LLM infrastructure initiatives focused on observability, evaluation, and safe integration patterns across AWS, Azure, and GCP. I build end-to-end systems for agentic workflows and RAG—designing MCP servers/clients, integrating Azure OpenAI and AWS Bedrock (including the Claude model family), and implementing monitoring for latency/throughput, drift, and quality degradation. I enjoy turning complex requirements into well-instrumented, secure, and scalable services using Python, FastAPI, Kubernetes, Terraform, and strong API lifecycle practices.

Poorna Chandra Reddy Padamati

AI Engineer, Data Scientist, Software Engineer, +2





I’m an AI Infrastructure Engineer with 9+ years of experience building distributed systems, production APIs, and managed cloud platforms that power reliable AI features. Over the last 3+ years, I’ve led GenAI/LLM infrastructure initiatives focused on observability, evaluation, and safe integration patterns across AWS, Azure, and GCP. I build end-to-end systems for agentic workflows and RAG—designing MCP servers/clients, integrating Azure OpenAI and AWS Bedrock (including the Claude model family), and implementing monitoring for latency/throughput, drift, and quality degradation. I enjoy turning complex requirements into well-instrumented, secure, and scalable services using Python, FastAPI, Kubernetes, Terraform, and strong API lifecycle practices.…I’m an AI Infrastructure Engineer with 9+ years of experience building distributed systems, production APIs, and managed cloud platforms that power reliable AI features. Over the last 3+ years, I’ve led GenAI/LLM infrastructure initiatives focused on observability, evaluation, and safe integration patterns across AWS, Azure, and GCP. I build end-to-end systems for agentic workflows and RAG—designing MCP servers/clients, integrating Azure OpenAI and AWS Bedrock (including the Claude model family), and implementing monitoring for latency/throughput, drift, and quality degradation. I enjoy turning complex requirements into well-instrumented, secure, and scalable services using Python, FastAPI, Kubernetes, Terraform, and strong API lifecycle practices.

Available to hire

I’m an AI Infrastructure Engineer with 9+ years of experience building distributed systems, production APIs, and managed cloud platforms that power reliable AI features. Over the last 3+ years, I’ve led GenAI/LLM infrastructure initiatives focused on observability, evaluation, and safe integration patterns across AWS, Azure, and GCP.

I build end-to-end systems for agentic workflows and RAG—designing MCP servers/clients, integrating Azure OpenAI and AWS Bedrock (including the Claude model family), and implementing monitoring for latency/throughput, drift, and quality degradation. I enjoy turning complex requirements into well-instrumented, secure, and scalable services using Python, FastAPI, Kubernetes, Terraform, and strong API lifecycle practices.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Work Experience

GenAI Engineer at Thinking Machines Lab

July 1, 2025 - Present

Delivered healthcare payer-provider production agentic AI systems for prior-authorization, utilization management, care coordination, and clinical documentation workflows. Built LangGraph/LangChain multi-agent orchestration with stateful control flow, shared memory, conditional routing, retries, and multi-step execution. Implemented MCP tool-calling patterns exposing authorized internal claims/eligibility/utilization APIs, plus RAG pipelines using FAISS, Pinecone, and Milvus with optimized chunking/embeddings and grounding. Developed high-throughput FastAPI services (async Python, streaming responses, schema-driven validation) and integrated Azure OpenAI Service and AWS Bedrock/Claude with token budgeting and deterministic structured outputs. Established evaluation workflows (RAGAS + custom harnesses) and observability across Prometheus, Azure Monitor, Evidently AI, and SQL audit logging, including drift/performance monitoring. Deployed inference services on Docker/Kubernetes/AKS with

AI/ML Engineer at Agiloft, Inc.

September 1, 2023 - June 30, 2025

Supported banking and financial-services clients by building production RAG and GenAI pipelines for contract lifecycle management (CLM), processing loan agreements, credit facility agreements, and compliance documents. Built enterprise RAG with LangChain and Pinecone (ingestion, chunking, embeddings, vector indexing, retrieval chains, and question answering). Created async FastAPI backend services for embedding generation, retrieval, prompt assembly, and LLM inference with validation and standardized response contracts. Developed automated evaluation workflows for retrieval relevance, answer faithfulness, context coverage, citation accuracy, and response consistency across ingestion/chunking/retrieval configurations. Monitored latency and retrieval performance using Azure Monitor and Grafana; collaborated on API contracts and secured credentials via Azure Key Vault. Containerized services and deployed across AKS environments, partnering on runtime configuration and resource sizing. Als

Data Scientist (Machine Learning) at LTI Mindtree

April 1, 2022 - August 31, 2023

Developed machine learning models for risk scoring, customer segmentation, and behavioral analytics with interpretability (SHAP/LIME) and controlled experimentation (A/B testing, causal inference, uplift/propensity, forecasting). Automated end-to-end ML lifecycle on AWS: data preparation, orchestration, training, batch scoring, and monitoring. Built pipelines with Apache Airflow and tracked experiments and dataset versions using MLflow and DVC for reproducibility. Served predictions via TensorFlow Serving and Dockerized services on Kubernetes for downstream consumption. Implemented Prometheus/Grafana monitoring and used GitHub Actions for release validation. Produced business-ready insights by translating statistical results into recommendations for stakeholders.

Data Scientist – NLP at Zensar Technologies

September 1, 2018 - December 31, 2021

Built NLP solutions for text classification and information extraction across business documents, focusing on reusable preprocessing pipelines and supervised model development. Wrote SQL/Python scripts to extract, clean, normalize, validate, and prepare datasets. Developed feature extraction and vectorization workflows using Python with spaCy and NLTK, and trained predictive models with XGBoost/LightGBM and statistical analysis using Pandas/NumPy/Statsmodels. Supported Dockerized deployments, release testing, and Git-based version control in collaboration with data scientists, analysts, and developers.

Data Scientist at Fractal Analytics

April 1, 2017 - August 31, 2018

Created classification and segmentation models and built large-scale customer analytics data pipelines using Hadoop-based datasets and distributed processing on AWS EMR. Queried and transformed data with SQL and PySpark for reporting and machine learning. Implemented targeting models and supported rule-based cross-sell/up-sell recommendations. Automated recurring batch processing with Apache Airflow and delivered dashboards using Tableau and Power BI. Debugged SQL/PySpark pipeline failures and managed refresh workflows and data transformations at scale.