I’m an AI Software Engineer with 4+ years of experience building production-grade AI systems, backend services, and cloud-native platforms—especially for retrieval-augmented generation (RAG), agentic AI, and LLM evaluation. I’ve delivered enterprise solutions in financial services and large organizations, focusing on secure knowledge discovery, compliance research, and operational intelligence using tools like FastAPI, Azure OpenAI, Amazon Bedrock, LangChain/LangGraph, Kafka, Redis, and Kubernetes. I enjoy turning complex requirements into reliable systems by designing scalable retrieval and document intelligence pipelines, building event-driven workflows for throughput and resilience, and implementing LLMOps/MLOps with strong observability. I partner closely with engineering, product, security, and compliance stakeholders to ship AI platforms that are fast, accurate, and governed for real-world production reliability.

Varsha Reddy Arava

I’m an AI Software Engineer with 4+ years of experience building production-grade AI systems, backend services, and cloud-native platforms—especially for retrieval-augmented generation (RAG), agentic AI, and LLM evaluation. I’ve delivered enterprise solutions in financial services and large organizations, focusing on secure knowledge discovery, compliance research, and operational intelligence using tools like FastAPI, Azure OpenAI, Amazon Bedrock, LangChain/LangGraph, Kafka, Redis, and Kubernetes. I enjoy turning complex requirements into reliable systems by designing scalable retrieval and document intelligence pipelines, building event-driven workflows for throughput and resilience, and implementing LLMOps/MLOps with strong observability. I partner closely with engineering, product, security, and compliance stakeholders to ship AI platforms that are fast, accurate, and governed for real-world production reliability.

Available to hire

I’m an AI Software Engineer with 4+ years of experience building production-grade AI systems, backend services, and cloud-native platforms—especially for retrieval-augmented generation (RAG), agentic AI, and LLM evaluation. I’ve delivered enterprise solutions in financial services and large organizations, focusing on secure knowledge discovery, compliance research, and operational intelligence using tools like FastAPI, Azure OpenAI, Amazon Bedrock, LangChain/LangGraph, Kafka, Redis, and Kubernetes.

I enjoy turning complex requirements into reliable systems by designing scalable retrieval and document intelligence pipelines, building event-driven workflows for throughput and resilience, and implementing LLMOps/MLOps with strong observability. I partner closely with engineering, product, security, and compliance stakeholders to ship AI platforms that are fast, accurate, and governed for real-world production reliability.

See more

Experience Level

Expert
Expert
Expert
Expert
Expert
Expert
Expert
Intermediate
Intermediate
Intermediate
See more

Language

Work Experience

AI Software Engineer at JPMorgan Chase & Co.
January 1, 2026 - Present
Designed and deployed enterprise AI applications using Python, Azure OpenAI, Amazon Bedrock, LangChain, and RAG to support secure knowledge discovery, regulatory research, and operational intelligence. Architected scalable retrieval services with hybrid search, vector databases, embeddings, and reranking to search 500K+ documents and improve retrieval speed and relevance. Built document intelligence pipelines using OCR, NLP, and LLMs to extract, classify, summarize, and analyze contracts and compliance documents, reducing manual review effort by ~65%. Developed low-latency backend services with FastAPI, SQLAlchemy, AsyncIO, Kafka, and Redis, and implemented event-driven workflows for resilience and horizontal scalability. Established automated LLM evaluation and observability using LangSmith, RAGAS, and DeepEval to improve response-quality reliability and reduce hallucination risk, and built reusable platform components for agent orchestration, memory, and tool calling.
Software Engineer at KPIT
February 1, 2023 - August 31, 2024
Developed enterprise backend services using Python, Java, SQL, and REST APIs for business-critical applications and distributed workflows. Designed scalable microservices and API integrations for high-volume systems to improve responsiveness, reliability, and horizontal scalability. Built data integration services processing 10M+ records per month to automate data movement and transformation workflows. Implemented Kafka-based event-driven integrations for real-time messaging and resilient asynchronous processing. Optimized SQL queries, indexing, and data-access patterns to reduce report generation time by ~40%, and improved quality by implementing testing with Pytest and CI/CD workflows using Git-based delivery.
Software Engineer at HCLTech
July 1, 2020 - February 1, 2023
Developed and maintained enterprise software applications using Python, Java, SQL, and REST APIs for business-critical platforms. Implemented asynchronous processing and messaging patterns to increase scalability and reduce coupling between distributed services. Optimized database queries and application workflows to improve response times and operational performance. Built automated unit and integration tests with Pytest and supported continuous integration to improve release stability. Investigated production incidents using logging, monitoring, and root-cause analysis to improve reliability and reduce recurring operational issues.

Education

Master in Computer Science at University of Dayton
January 1, 2024 - May 1, 2026
Bachelor in Computer Science at JNTUA College of Engineering
January 1, 2017 - June 1, 2021

Qualifications

Add your qualifications or awards here.

Industry Experience

Financial Services, Software & Internet, Professional Services, Computers & Electronics

Experience Level

Expert
Expert
Expert
Expert
Expert
Expert
Expert
Intermediate
Intermediate
Intermediate
See more