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

I am an AI/ML Engineer with 5+ years of production experience architecting LLM-powered systems, enterprise RAG pipelines, and agentic ML workflows across telecom and healthcare verticals. I have hands-on expertise in LLM orchestration (OpenAI, Anthropic Claude), hybrid dense/sparse retrieval, vector database integration, and automated model evaluation. I strive to drive measurable operational outcomes by deploying scalable systems that reduce analyst review time, automate data triage, and improve prediction precision at enterprise scale. I am actively pursuing AI Engineer, ML Engineer, and Applied AI roles where infrastructure depth and production reliability matter. I enjoy collaborating with cross-functional teams, delivering reliable production ML features, and continuously improving data pipelines and developer tooling to accelerate decision making and outcomes.…I am an AI/ML Engineer with 5+ years of production experience architecting LLM-powered systems, enterprise RAG pipelines, and agentic ML workflows across telecom and healthcare verticals. I have hands-on expertise in LLM orchestration (OpenAI, Anthropic Claude), hybrid dense/sparse retrieval, vector database integration, and automated model evaluation. I strive to drive measurable operational outcomes by deploying scalable systems that reduce analyst review time, automate data triage, and improve prediction precision at enterprise scale. I am actively pursuing AI Engineer, ML Engineer, and Applied AI roles where infrastructure depth and production reliability matter. I enjoy collaborating with cross-functional teams, delivering reliable production ML features, and continuously improving data pipelines and developer tooling to accelerate decision making and outcomes.

Pradeep Varma Ganapathiraju

AI Engineer, AI Developer, Data Scientist, +2





I am an AI/ML Engineer with 5+ years of production experience architecting LLM-powered systems, enterprise RAG pipelines, and agentic ML workflows across telecom and healthcare verticals. I have hands-on expertise in LLM orchestration (OpenAI, Anthropic Claude), hybrid dense/sparse retrieval, vector database integration, and automated model evaluation. I strive to drive measurable operational outcomes by deploying scalable systems that reduce analyst review time, automate data triage, and improve prediction precision at enterprise scale. I am actively pursuing AI Engineer, ML Engineer, and Applied AI roles where infrastructure depth and production reliability matter. I enjoy collaborating with cross-functional teams, delivering reliable production ML features, and continuously improving data pipelines and developer tooling to accelerate decision making and outcomes.…I am an AI/ML Engineer with 5+ years of production experience architecting LLM-powered systems, enterprise RAG pipelines, and agentic ML workflows across telecom and healthcare verticals. I have hands-on expertise in LLM orchestration (OpenAI, Anthropic Claude), hybrid dense/sparse retrieval, vector database integration, and automated model evaluation. I strive to drive measurable operational outcomes by deploying scalable systems that reduce analyst review time, automate data triage, and improve prediction precision at enterprise scale. I am actively pursuing AI Engineer, ML Engineer, and Applied AI roles where infrastructure depth and production reliability matter. I enjoy collaborating with cross-functional teams, delivering reliable production ML features, and continuously improving data pipelines and developer tooling to accelerate decision making and outcomes.

Available to hire

I am an AI/ML Engineer with 5+ years of production experience architecting LLM-powered systems, enterprise RAG pipelines, and agentic ML workflows across telecom and healthcare verticals. I have hands-on expertise in LLM orchestration (OpenAI, Anthropic Claude), hybrid dense/sparse retrieval, vector database integration, and automated model evaluation. I strive to drive measurable operational outcomes by deploying scalable systems that reduce analyst review time, automate data triage, and improve prediction precision at enterprise scale. I am actively pursuing AI Engineer, ML Engineer, and Applied AI roles where infrastructure depth and production reliability matter.

I enjoy collaborating with cross-functional teams, delivering reliable production ML features, and continuously improving data pipelines and developer tooling to accelerate decision making and outcomes.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Work Experience

AI Engineer (Agentic) at T-Mobile

June 1, 2025 - Present

Architected a multi-step LLM agentic workflow using LangChain and OpenAI function-calling to autonomously diagnose network performance degradation— orchestrating tool calls across telemetry APIs, knowledge retrieval, and alert generation—reducing mean time to detection by ~40% over prior manual triage processes. Built an agentic customer support pipeline with deterministic state-machine guardrails, routing natural-language tickets through intent classification, context retrieval, and LLM-generated response drafts, automating resolution for 60% of inbound volume and cutting average handling time by 28%. Implemented enterprise RAG system indexing internal runbooks and playbooks with source-cited responses, reducing escalation lookup time by 45%. Deployed and tuned semantic chunking and hybrid retrieval strategies to maximize context window usage and grounding accuracy across multi-hop telecom documentation.

AI Engineer at The Cigna Group

October 1, 2024 - May 1, 2025

Architected an enterprise RAG pipeline indexing 50K+ clinical guidelines and policy documents, enabling staff to query institutional protocols with source-cited responses and reducing manual lookup time by 45%. Implemented semantic chunking and context injection to improve factual grounding across clinical knowledge tasks. Built an LLM-powered clinical decision support feature to summarize patient intake notes and surface high-risk indicators, reducing clinician chart review time by ~30% across pilots. Designed REST API pipelines connecting LLM inference to a production healthcare operations dashboard, cutting average task decision latency by 25% and improving data completeness for downstream analytics by 38%.

AI Engineer at New Jersey Institute of Technology

November 1, 2023 - May 1, 2024

Conducted graduate AI research on LLM prompt optimization and context window management, evaluating output consistency across model architectures using automated benchmarking pipelines. Built an NLP data preprocessing and embedding pipeline to enable downstream fine-tuning experiments. Built a RAG prototype using LangChain and FAISS to evaluate retrieval quality over 5,000+ research abstracts, comparing dense embedding retrieval against keyword-based baselines.

ML Engineer at Accenture

June 1, 2021 - August 1, 2023

Designed and optimized PostgreSQL schemas and data ingestion pipelines for large-scale datasets, improving retrieval throughput through index tuning and query restructuring. Built and deployed REST API inference services supporting ML model scoring for a platform with 500+ concurrent users, achieving sub-200ms response times at peak load. Implemented real-time prediction and dynamic validation modules with adaptive feedback, increasing average user engagement by 20%. Delivered multiple end-to-end ML features across data, API, and application layers in agile sprints, accelerating release velocity.