Tanish Gupta

Associate Consultant

Bengaluru, Karnataka, India7 yrs 8 mos experience

Highly StableAI Enabled

Key Highlights

Expert in building production-grade LLM platforms.
Proficient in automating SDLC with AI solutions.
Strong experience in cloud-native architecture.

Stackforce AI infers this person is a SaaS expert specializing in AI-driven solutions for enterprise-scale applications.

Contact

Skills

Core Skills

Generative AiCloud-native Ai SolutionsLlm

Other Skills

AgenticAIC (Programming Language)C++CI/CDCascading Style Sheets (CSS)Cloud FunctionsConfluenceDeepSeekDockerEventarcExpress.jsFAISSFigmaGitHubGoogle Cloud Platform (GCP)

About

I am an AI & Full-Stack Engineer with 4+ years of hands-on experience building production-grade LLM platforms, Retrieval-Augmented Generation (RAG) systems, and multi-agent architectures at enterprise scale. I currently work on Cognizant Neuro AI, where I design and deploy cloud-native, serverless AI solutions on Google Cloud that automate large parts of the Software Development Lifecycle (SDLC). My core strength lies in taking Generative AI from PoC to large-scale production—owning everything from data ingestion, vector indexing, orchestration, model integration, CI/CD, observability, and enterprise tool integrations. 💡 I enjoy solving hard engineering problems where AI meets real business workflows and I thrive in 0→1 product environments as well as large enterprise platforms. 📩 Always open to discussions on Senior AI Engineer, LLM Engineer, and Full-Stack AI roles.

Experience

7 yrs 8 mos

Total Experience

3 yrs 8 mos

Average Tenure

5 mos

Current Experience

Ey

Senior Consultant

Jan 2026 – Present · 5 mos · Bengaluru, Karnataka, India · Hybrid

Cognizant

3 roles

Technology Analyst

Promoted

Oct 2023 – Dec 2025 · 2 yrs 2 mos

Core contributor to an enterprise AI platform powering the end-to-end Project Development Lifecycle for multiple Fortune clients.
Architected event-driven RAG pipelines using Vector Search DB + RagManaged DB on Google Cloud Run, enabling low-latency enterprise knowledge retrieval at scale.
Designed high-throughput ingestion pipelines using GCS, Pub/Sub, and Dataflow, processing 100k+ documents/month.
Built fully serverless orchestration with Eventarc & Cloud Functions, eliminating VM management and reducing infra ops by ~60%.
Implemented production-grade CI/CD using Cloud Build + Docker, supporting zero-downtime releases.
Designed MCP integrations with JIRA, Confluence, GitHub & Figma, enabling real-time AI-driven SDLC automation.
Developed a User Story AI Agent using ADK and Langgraph, improving requirement clarity and sprint readiness by ~40%.
Led onboarding of multiple enterprise clients, establishing the platform as a core AI backbone for delivery teams.

Retrieval-Augmented Generation (RAG)Google Cloud Platform (GCP)Vector DBEventarcCloud FunctionsCI/CD+7

Technology Engineer

Jul 2022 – Sep 2023 · 1 yr 2 mos

Built an LLM-powered QA copilot for test case generation, defect triage, and story validation.
Reduced manual QA effort by ~50% and improved regression cycle time.
Implemented LangGraph multi-agent workflows with WebSockets streaming + RabbitMQ orchestration.
Designed a RAG system using OpenAI, Neo4j, DeepSeek & FAISS for contextual test intelligence.
Delivered production usage across 15+ enterprise programs via GitHub & Azure Boards integrations

LLMLangGraphWebSocketsRabbitMQRAGOpenAI+4