Hi there! I'm Priya Kunam, an AI/ML engineer with 3+ years of experience delivering production-grade Generative AI solutions, including RAG pipelines and autonomous agent workflows. I enjoy turning complex business challenges into practical, scalable AI systems that enable intelligent decision-making across enterprise platforms. I have hands-on experience integrating OpenAI, Azure OpenAI, and Hugging Face APIs, designing vector-based retrieval with FAISS, Pinecone, and Weaviate, and implementing guardrails, prompt optimization, and PII/PHI handling in production. I thrive in Docker/Kubernetes environments with CI/CD for ML pipelines, monitoring, and observability to ensure reliable, secure AI services.

Priya Kunam

Hi there! I'm Priya Kunam, an AI/ML engineer with 3+ years of experience delivering production-grade Generative AI solutions, including RAG pipelines and autonomous agent workflows. I enjoy turning complex business challenges into practical, scalable AI systems that enable intelligent decision-making across enterprise platforms. I have hands-on experience integrating OpenAI, Azure OpenAI, and Hugging Face APIs, designing vector-based retrieval with FAISS, Pinecone, and Weaviate, and implementing guardrails, prompt optimization, and PII/PHI handling in production. I thrive in Docker/Kubernetes environments with CI/CD for ML pipelines, monitoring, and observability to ensure reliable, secure AI services.

Available to hire

Hi there! I’m Priya Kunam, an AI/ML engineer with 3+ years of experience delivering production-grade Generative AI solutions, including RAG pipelines and autonomous agent workflows. I enjoy turning complex business challenges into practical, scalable AI systems that enable intelligent decision-making across enterprise platforms.

I have hands-on experience integrating OpenAI, Azure OpenAI, and Hugging Face APIs, designing vector-based retrieval with FAISS, Pinecone, and Weaviate, and implementing guardrails, prompt optimization, and PII/PHI handling in production. I thrive in Docker/Kubernetes environments with CI/CD for ML pipelines, monitoring, and observability to ensure reliable, secure AI services.

See more

Experience Level

Expert
Expert
Expert
Intermediate

Work Experience

AI/ML Engineer at Fortune Cloud Solutions
June 1, 2025 - Present
Designed and implemented enterprise-grade AI systems to support financial document processing, risk analysis, and intelligent automation. Built Retrieval-Augmented Generation (RAG) pipelines and autonomous agent workflows for context-aware querying and decision-making across large-scale mortgage datasets. Implemented MCP-based integrations to enable secure data access, designed AI guardrails, optimized costs and latency, and deployed production services using Docker and Kubernetes with CI/CD pipelines. Established monitoring and observability dashboards to track latency, token usage, and model quality signals.
AI/ML Engineer at Webmatics Solutions Pvt Ltd
April 1, 2021 - July 1, 2023
Developed production-grade AI/ML systems focusing on NLP-driven document processing, semantic search, and early RAG workflows. Built agentic workflows using LangChain and AutoGPT, designed data pipelines with PySpark, integrated LLMs via API-based services, and implemented prompt optimization and memory handling for improved accuracy. Managed end-to-end model lifecycle and ensured secure handling of sensitive data with governance controls.

Education

Master’s in Computer Science at University of Central Missouri
August 1, 2023 - May 1, 2025

Qualifications

Add your qualifications or awards here.

Industry Experience

Financial Services, Software & Internet

Experience Level

Expert
Expert
Expert
Intermediate