> experience

Where I've shipped

> forward deployed engineering

The role I actually do: ship into enterprise environments end to end, from cold-start discovery through architecture, implementation, and production deployment inside customer-managed clouds. Comfortable as the sole engineer on a zero-to-one build or embedded inside a customer's engineering team.

customer-facing engineeringsolutions architecturecustomer discoverystakeholder alignmentmulti-tenant architecturecloud optimizationLLM token & cost engineeringinfrastructure optimizationidentity & SSO architectureproduction deployment

$ customer-facing work

▸Took an agentic quality-engineering platformClick to explore this project in detail from feasibility framing through production rollout to 17 enterprise QA teams at peak adoption.
▸Built the case for an enterprise conversational RAGClick to explore this project in detail redesign through customer usage analysis showing the rule-based system failing outside its predefined set, then owned the rollout end to end.
▸Took Loop CopilotClick to explore this project in detail from customer discovery through V2 inside a Fortune 500 sales org, where the pilot drove a V2 expansion request within two weeks.

$ architecture-level work

▸Deployed one codebase across customer-managed AWS, Azure, and GCP, adapting architecture, compute sizing, and identity (Azure AD, IAM, SSO) to each tenant's cloud with no forks.
▸Engineered advanced RAG from scratch: GraphRAGSee GraphRAG in the Mind Map on Neo4j with entity normalization, reranking, context compression, metadata filtering, query rerouting, and guardrails.
▸Secured multi-tenant isolation with tenant-aware RBAC: module-level CRUD-X permissions and role templates that onboard new enterprise customers without rebuilding the permission model.

$ cost, cloud, and token optimization

▸Cut per-tenant LLM spend through token and cost engineering: context compression, prompt-payload reduction, and rerouting low-complexity queries to lighter models.
▸Built the LLM observability and FinOps layer beneath it: per-tenant cost telemetry plus quality evaluation (Acceptance Criteria Coverage, Test Design Coverage, RAGAS).
▸Adapted compute sizing per tenant cloud so the same platform runs efficiently in each customer's environment.

$ stakeholder interactions

▸Customer stakeholders use the cost and quality telemetry live to track spend and output quality.
▸Designed the D365 integration inside the customer's tenant trust model: Power Automate flows authenticated by internal tenant identity, with direct Dataverse REST via MSAL held in reserve for environments that grant broader permissions.
▸Drove production hallucination from ~15% to under 5% via GraphRAGSee GraphRAG in the Mind Map and entity normalization, the accuracy bar enterprise QA teams held the platform to.

> timeline

Coforge

Senior Engineer · GenAI & Agentic AI

March 2024 - Present · Hyderabad, India

Architected and shipped an AI-infused agentic quality-engineering platformClick to explore this project in detail end to end, from feasibility framing through production rollout to 17 enterprise QA teams at peak adoption, deployed across customer-managed AWS, Azure, and GCP, adapting architecture and identity to each tenant's cloud.

Drove production hallucination from ~15% to under 5% by engineering advanced RAG from scratch: GraphRAGSee GraphRAG in the Mind Map on Neo4j with entity normalization, reranking, context compression, metadata filtering, query rerouting, and guardrails, with Agentic RAG over Jira and Azure DevOps to scope test generation.

Cut manual effort on covered test-authoring and triage workflows ~85% through agentic test generation, execution, and CI-integrated automation, and built a custom Playwright MCP integration that generates production-grade Playwright and Cypress scripts from natural language, cutting authoring time ~75%.

Engineered an LLM observability layer with per-tenant cost telemetry and quality evaluation (Acceptance Criteria Coverage, Test Design Coverage, RAGAS), and built tenant-aware RBAC with module-level CRUD-X permissions and role templates that onboard new customers without rebuilding permissions.

Hewlett Packard Enterprise

Data Scientist · Generative AI, ML & Conversational AI

November 2022 - December 2023 · Bangalore, India

Architected the migration of an enterprise conversational systemClick to explore this project in detail from rule-based FAQ to LLM-assisted RAG over a corpus of ~1,700 internal documents, cutting repeat user escalations ~40%.

Designed the retrieval pipeline end to end: chunking with overlap calibration, hybrid search combining semantic and keyword signals, and metadata filtering tuned for enterprise-jargon queries, with evaluation loops measuring retrieval precision against a held-out set and improving response relevance 30-40% in pilot.

Built the case for the retrieval-augmented redesign through customer usage analysis showing the rule-based system failing outside its predefined set, and owned the rollout end to end.

At HPE I also delivered the National Census Digital AssistantClick to explore this project in detail on Azure, a civic-scale conversational assistant that grounds guideline and FAQ answers with RAG while running enrolment and birth and death reporting as deterministic, audited state-machine flows.

Mphasis

Associate Software Engineer · Machine Learning & Data Science

July 2019 - October 2022 · Bangalore, India

Built fraud-detection and risk-scoring models for financial-services clients using tree-based ensembles (XGBoost, LightGBM, Random Forest) with engineered feature pipelines, improving precision ~15% over legacy rule-based systems and cutting manual review volume.

Developed predictive-analytics models and live streaming dashboards on investment data, enabling portfolio teams to act on signals without batch-reporting delays.

This early-career work is written up as Financial Risk & Fraud IntelligenceClick to explore this project in detail, with the modeling decisions and the move off rule-based systems.