

AI/ML Engineer with 9+ years of experience building scalable LLM-powered and agentic systems, delivering high-accuracy NLP solutions through robust prompt engineering and evaluation frameworks. Expertise in distributed systems, asynchronous processing, and cloud-based microservices (GCP), with a proven track record of developing high-throughput, production-grade AI pipelines focused on performance, reliability, and scalability.
• Designed and deployed scalable LLM-based pipelines for medical NLP and radiology entity extraction, delivering high-accuracy structured outputs (JSON/YAML), with strict schema enforcement.
• Built and optimized prompt engineering frameworks, significantly improving consistency, reliability, and domain-specific accuracy of model responses.
• Integrated Qwen-based LLMs into production systems using asynchronous APIs, achieving low latency, fault tolerance, and high throughput inference at scale.
• Developed agentic workflows, enabling multi-step reasoning, autonomous task execution, and dynamic tool integration for complex medical use cases.
• Architected modular, event-driven microservices using GCP (Pub/Sub, BigQuery), enabling scalable, real-time orchestration, and data processing pipelines.
• Implemented custom LLM evaluation frameworks (GEval, Deepeval) with domain-specific metrics, improving validation accuracy, and enabling continuous performance monitoring.
• Built high-throughput concurrent processing systems (Python async/await, threading), optimizing parallel execution for large-scale LLM inference, and evaluation workloads.
• Containerized and deployed distributed systems using Docker and Kubernetes, ensuring scalability, reliability, and production-grade observability (logging, monitoring, debugging).
• Provided technical leadership and architectural guidance for the design and implementation of complex system enhancements.
• Developed and maintained high-quality applications using Java/Spring, leveraging strong expertise in SQL, PL/SQL, XML, Unix, and shell scripting.
• Built and optimized multi-threaded and messaging-based systems, ensuring high performance and reliability.
• Led production support efforts, proactively resolving critical issues, and coordinating with cross-functional teams to ensure system stability.
• Drove technical excellence by promoting reusable design patterns, identifying gaps in existing codebases, and evaluating the feasibility of proposed solutions.
• Collaborated closely with engineering and business stakeholders to gather requirements, define project scope, and deliver high-impact solutions.
• Ensured compliance with architectural standards, security policies, and risk management practices across all deliverables.
Operated effectively within a structured SDLC (Waterfall), contributing to planning, development, and delivery phases, while resolving issues in a collaborative team environment.
AI/ML & LLMs: LLMs, Prompt Engineering, Agentic Systems, NLP
Languages: Java, J2EE, Python
Frameworks & APIs: Spring, Spring boot, Fast APIs, Rest APIs, Async APIs
Database: mongoDB, MySql, Postgres, BigQuery
Cloud Platform: AWS, Azure, GCP
Post Graduate Degree in Machine Learning and AI Simplilearn in collaboration with Purdue university