Sharma G profile photo 1 on Tal

Sharma G

AgentOps/MLOps Engineer

Srirangam

1+ year of work experience

Tata Consultancy Services
Dec 20241 yr 5 mosPresent

Chennai, Tamil Nadu, India

Served as a core member of the MLOps and AgentOps team, bridging the gap between Generative AI development and enterprise-scale operations. Focused on architecting, securing, and monitoring autonomous agents within the Google Cloud ecosystem to ensure high availability and compliance. · Overcame the challenge of monitoring non-deterministic LLM behavior by establishing a comprehensive observability suite using Datadog and Langfuse, resulting in real-time visibility into agent latency, cost, and accuracy. · Streamlined the complex lifecycle of AI agents by architecting multi-stage CI/CD pipelines (Dev, Sandbox, Pre-prod, Prod), eliminating manual deployment errors and ensuring consistent releases across environments. · Solved the issue of stateless LLM interactions by designing a persistent memory architecture with AlloyDB and Vertex AI Agent Engine, enabling agents to maintain long-term context and manage active user sessions effectively. · Mitigated risks associated with Generative AI deployment by implementing robust security guardrails, ensuring all agent outputs adhered to strict enterprise compliance and safety standards.

Education

psna college of engineering and technology

Bachelor of Engineering, Electronics and Communications Engineering

psna college of engineering and technology

20204 yrs2024

High School

Pannai Matriculation Higher Secondary School

20191 yr2020

Join Sharma and 10k+ other professionals on

Tal Boss

Tal is the app where bosses meet engineers & builders directly, without middlemen

Download Tal Boss

Sharma G on Tal

Headline

AgentOps/MLOps Engineer

About

AgentOps Engineer & AI Solutions Architect Results-oriented Agent Developer specializing in the lifecycle management of production-grade AI agents using the Google Agent Development Kit (ADK) and Vertex AI. Expert in architecting robust ML pipelines and deploying scalable solutions on Google Cloud Platform (GCP), specifically utilizing Cloud Run and Vertex AI Agent Engine. Proven track record in implementing LLM observability, optimizing Model Context Protocol (MCP) architectures, and ensuring seamless Agent-to-Agent (A2A) communication. Adept at bridging the gap between model development and operational excellence.

Location

Srirangam

Work experience

System Engineer at Tata Consultancy Services, Dec 2024 - Present · 1 yr 5 mos, Chennai, Tamil Nadu, India, Served as a core member of the MLOps and AgentOps team, bridging the gap between Generative AI development and enterprise-scale operations. Focused on architecting, securing, and monitoring autonomous agents within the Google Cloud ecosystem to ensure high availability and compliance. · Overcame the challenge of monitoring non-deterministic LLM behavior by establishing a comprehensive observability suite using Datadog and Langfuse, resulting in real-time visibility into agent latency, cost, and accuracy. · Streamlined the complex lifecycle of AI agents by architecting multi-stage CI/CD pipelines (Dev, Sandbox, Pre-prod, Prod), eliminating manual deployment errors and ensuring consistent releases across environments. · Solved the issue of stateless LLM interactions by designing a persistent memory architecture with AlloyDB and Vertex AI Agent Engine, enabling agents to maintain long-term context and manage active user sessions effectively. · Mitigated risks associated with Generative AI deployment by implementing robust security guardrails, ensuring all agent outputs adhered to strict enterprise compliance and safety standards.

Education

Bachelor of Engineering, Electronics and Communications Engineering, psna college of engineering and technology

High School, Pannai Matriculation Higher Secondary School

Sharma G - System Engineer in Srirangam | Tal