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

Hi, I’m Keerthi Annarapu, a software engineer focused on AI and backend systems. I design and ship scalable, observable AI-powered workflows, agent-based automation, and data-driven decision intelligence for enterprise applications. I enjoy turning complex problems into reliable systems and collaborating with ML researchers and product teams to deliver meaningful, auditable AI outputs. I thrive in fast-paced environments, applying responsible AI practices, rigorous testing, and strong governance to build trustworthy solutions that scale.…Hi, I’m Keerthi Annarapu, a software engineer focused on AI and backend systems. I design and ship scalable, observable AI-powered workflows, agent-based automation, and data-driven decision intelligence for enterprise applications. I enjoy turning complex problems into reliable systems and collaborating with ML researchers and product teams to deliver meaningful, auditable AI outputs. I thrive in fast-paced environments, applying responsible AI practices, rigorous testing, and strong governance to build trustworthy solutions that scale.

Keerthi Annarapu

AI Engineer, Data Scientist, Full Stack Developer, +2





Hi, I’m Keerthi Annarapu, a software engineer focused on AI and backend systems. I design and ship scalable, observable AI-powered workflows, agent-based automation, and data-driven decision intelligence for enterprise applications. I enjoy turning complex problems into reliable systems and collaborating with ML researchers and product teams to deliver meaningful, auditable AI outputs. I thrive in fast-paced environments, applying responsible AI practices, rigorous testing, and strong governance to build trustworthy solutions that scale.…Hi, I’m Keerthi Annarapu, a software engineer focused on AI and backend systems. I design and ship scalable, observable AI-powered workflows, agent-based automation, and data-driven decision intelligence for enterprise applications. I enjoy turning complex problems into reliable systems and collaborating with ML researchers and product teams to deliver meaningful, auditable AI outputs. I thrive in fast-paced environments, applying responsible AI practices, rigorous testing, and strong governance to build trustworthy solutions that scale.

Available to hire

Hi, I’m Keerthi Annarapu, a software engineer focused on AI and backend systems. I design and ship scalable, observable AI-powered workflows, agent-based automation, and data-driven decision intelligence for enterprise applications. I enjoy turning complex problems into reliable systems and collaborating with ML researchers and product teams to deliver meaningful, auditable AI outputs.
I thrive in fast-paced environments, applying responsible AI practices, rigorous testing, and strong governance to build trustworthy solutions that scale.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Work Experience

Software Engineer – AI & Backend Systems at Walmart Global Tech

July 1, 2025 - December 1, 2025

Contributed to a large-scale LLM inference pipeline serving millions of enterprise users; implemented multi-agent orchestration and tool-calling workflows integrated with internal knowledge graph systems. Built event-driven microservices on cloud infrastructure enabling agentic workflow automation across supply chain decision intelligence. Designed and operated RAG pipelines with embedding and chunking strategies and hybrid retrieval (vector similarity + keyword) achieving sub-300ms p95 latency. Defined evaluation harnesses for agent behavior including hallucination detection, output coherence, and regression gates to enable CI/CD-integrated model lifecycle management. Collaborated with ML researchers and product teams to ship traceable, auditable AI outputs with full observability and structured logging.

Software Engineer – AI & Backend Systems at Cognizant Technology Solutions

November 1, 2020 - January 31, 2024

Designed and operated large-scale LLM inference pipelines serving 5,000+ enterprise users; implemented F1/AUC/precision-recall benchmarks and anomaly detection dashboards tracking embedding drift and model regression, reducing triage time by 60% and saving $50K+ in operational costs. Engineered high-throughput streaming data pipelines (2 TB/day) using Kafka, PySpark, Databricks, and Delta Lake with versioned configs and seeded runs for full experiment reproducibility. Built and deployed FastAPI microservices on Kubernetes (AWS EKS/Terraform) at sub-300ms latency; applied responsible AI practices including bias evaluation and output auditability across production LLM deployments. Evaluated transformer vs supervised baselines; contributed to CI/CD release gates using F1, AUC, and precision/recall; maintained pytest coverage for preprocessing and evaluation logic via PR-based code review. Designed GraphQL schema contracts between backend services and frontend clients; ensured contract sta

ML Intern at Coign Technologies

January 1, 2020 - April 30, 2020

Built backend REST APIs and ML data pipelines; contributed to automated evaluation frameworks and pytest testing infrastructure, establishing output quality benchmarks for production services. Projects include Energy Simulation Evaluation Pipeline (end-to-end grading using real IoT sensor logs vs digital-twin outputs with statistical metrics), Low-Latency RAG Inference Service (production GenAI microservice with automated hallucination detection and hybrid retrieval achieving <200ms p95 latency), MedDeserts – Agentic AI Pipeline (multi-agent processing of health records with strict quality thresholds), and ForgeAI – Open-Source GenAI developer tool.