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

I am a Senior AI/ML Engineer with 6 years of experience designing, building, and operating production-grade Generative AI, LLM, and ML systems at enterprise scale. I specialize in LLM application architecture, prompt engineering at scale, multi-provider orchestration, safety guardrails, and cost optimization. With a solid software engineering foundation in Python and Java, I design and operate systems on AWS and GCP with a strong emphasis on observability, reliability engineering, and scalable, maintainable design. I enjoy mentoring engineers and driving production-readiness through rigorous design reviews, testing, and governance.…I am a Senior AI/ML Engineer with 6 years of experience designing, building, and operating production-grade Generative AI, LLM, and ML systems at enterprise scale. I specialize in LLM application architecture, prompt engineering at scale, multi-provider orchestration, safety guardrails, and cost optimization. With a solid software engineering foundation in Python and Java, I design and operate systems on AWS and GCP with a strong emphasis on observability, reliability engineering, and scalable, maintainable design. I enjoy mentoring engineers and driving production-readiness through rigorous design reviews, testing, and governance.

Hemanth Tirumalarajukupam





I am a Senior AI/ML Engineer with 6 years of experience designing, building, and operating production-grade Generative AI, LLM, and ML systems at enterprise scale. I specialize in LLM application architecture, prompt engineering at scale, multi-provider orchestration, safety guardrails, and cost optimization. With a solid software engineering foundation in Python and Java, I design and operate systems on AWS and GCP with a strong emphasis on observability, reliability engineering, and scalable, maintainable design. I enjoy mentoring engineers and driving production-readiness through rigorous design reviews, testing, and governance.…I am a Senior AI/ML Engineer with 6 years of experience designing, building, and operating production-grade Generative AI, LLM, and ML systems at enterprise scale. I specialize in LLM application architecture, prompt engineering at scale, multi-provider orchestration, safety guardrails, and cost optimization. With a solid software engineering foundation in Python and Java, I design and operate systems on AWS and GCP with a strong emphasis on observability, reliability engineering, and scalable, maintainable design. I enjoy mentoring engineers and driving production-readiness through rigorous design reviews, testing, and governance.

Available to hire

I am a Senior AI/ML Engineer with 6 years of experience designing, building, and operating production-grade Generative AI, LLM, and ML systems at enterprise scale. I specialize in LLM application architecture, prompt engineering at scale, multi-provider orchestration, safety guardrails, and cost optimization.

With a solid software engineering foundation in Python and Java, I design and operate systems on AWS and GCP with a strong emphasis on observability, reliability engineering, and scalable, maintainable design. I enjoy mentoring engineers and driving production-readiness through rigorous design reviews, testing, and governance.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Work Experience

AI/ML Engineer at ServiceNow

November 1, 2024 - Present

Architected and led the development of enterprise-scale Generative AI platforms using GPT and Azure OpenAI, supporting multiple internal products with strict reliability, latency, and security requirements. Designed LLM application architecture with model routing, provider abstraction, fallback strategies, retries, timeout controls, and circuit breakers to ensure high availability across providers. Built prompt engineering frameworks at scale, including versioned templates, system prompts, tool calling, structured outputs, and automated evaluation pipelines. Implemented LLM safety and governance layers, including moderation workflows, prompt injection mitigation, policy enforcement, and hallucination reduction techniques. Developed usage analytics and cost-optimization pipelines, applying token budgeting, adaptive model selection, response truncation, and caching strategies, reducing LLM operational costs by 30%. Led design of event-driven AI workflows using AWS Step Functions, Lambda,

ML Engineer at Infinite Infolab

March 1, 2019 - December 1, 2023

Built and productionized transformer-based ML inference systems and hybrid rule-based + LLM architectures for personalization and intelligent automation use cases. Designed and deployed ML model serving pipelines, including batching, latency tuning, and inference optimization for real-time and batch workloads. Developed personalization and ranking systems with well-defined experiments, metrics, and error analysis workflows. Implemented ML monitoring, drift detection, and data quality validation, improving model stability and long-term performance. Built secure backend services using Python Flask, Celery, and asynchronous processing for scalable ML workflows. Designed multi-tenant architectures with strong isolation, RBAC, and JWT-based authentication. Automated CI/CD pipelines using Docker, Terraform, AWS SAM, and GitHub Actions, significantly improving deployment reliability and release velocity.