Headline

LLM / GenAI Lead Engineer | Building Enterprise AI Systems | LLM Infrastructure | Multi-Agent Systems | RAG | AI Platforms | LLMOps | AI Evaluation | Backend Architect | Python | AWS | Distributed Systems

About

I'm a GenAI and AI Infrastructure Engineer with 5+ years of experience building distributed backend systems, enterprise payment platforms, and production-ready AI applications. My current focus is designing scalable LLM systems, including Retrieval-Augmented Generation (RAG), Agentic AI, multi-agent workflows, AI developer platforms, LLM evaluation, semantic search, and AI observability. I enjoy solving challenges around latency, reliability, scalability, and cost optimization to build AI systems that are dependable in production. Before transitioning to Generative AI, I built high-throughput banking and payment systems, giving me a strong foundation in distributed systems, cloud-native architecture, and performance engineering. That experience shapes how I approach AI engineering—with reliability, maintainability, and operational excellence as first principles. Core Expertise: LLM Infrastructure • RAG • Agentic AI • AI Evaluation • Distributed Systems • Backend Architecture • Cloud Infrastructure Tech Stack: Python • FastAPI • Node.js • LangGraph • LangChain • OpenAI • Anthropic • AWS • Kubernetes • Docker • PostgreSQL • Redis • Neo4j • RabbitMQ I also enjoy sharing my learnings through technical writing and open-source projects focused on production AI systems.

Location

Bangalore Urban

AI stack

deepseek

hermes agent

langchain

langfuse

mistral

Ragas

Work experience

Lead Engineering at Pratishthan Software Ventures Pvt. Ltd, Apr 2026 - Present · 6 mos, Bengaluru, - Designed and engineered production-grade Retrieval-Augmented Generation (RAG) pipelines utilizing advanced hybrid retrieval and vector search to maximize context relevance and grounding quality. - Optimized embedding generation, semantic chunking strategies, and re-ranking pipelines, significantly improving retrieval accuracy while reducing LLM hallucination rates. - Engineered deterministic, multi-step agent workflows leveraging tool-calling, structured reasoning patterns, and LangGraph to automate complex enterprise tasks. - Implemented robust evaluation and observability pipelines to run accuracy scoring, regression testing, and real-time response validation for prompt updates and model transitions. - Drastically reduced inference latency and operational API costs by architecting semantic caching layers via Redis and optimizing upstream API routing. - Devised systematic prompt engineering and version control strategies to enforce output consistency and strict guardrails across enterprise-wide business workflows

Team Lead at Pratishthan Software Ventures Pvt. Ltd, Apr 2025 - Mar 2026 · 1 yr, Bengaluru, - Led a team working on LLM, Generative AI, and agentic AI systems, building production-grade AI workflows on a large enterprise payments platform. - Designed an infra-level code generation platform that converts LLD + configuration into one-click backend and infrastructure code, enforcing consistent architecture patterns across microservices. - Built a LangChain-based agent creation platform (Python, LangChain, OpenAI, Anthropic) enabling users to deploy AI agents via prompt + configuration with zero-code setup. - Developed a LLM-powered component test generation system that converts LLD + chat inputs into design-aware test suites, isolated from production releases to ensure stability during active development. - Architected a Neo4j-based code intelligence graph mapping services, APIs, and dependencies, and built an LLD design assistant that guides product teams step-by-step while surfacing impacted systems in real time. - Built scalable backend systems (Node.js, Python, microservices) supporting AI-driven workflows and high-throughput APIs. - Designed event-driven architectures using RabbitMQ for asynchronous execution of LLM tasks and agent workflows. - Worked on AWS cloud infrastructure (Lambda, EC2, Kubernetes) to deploy and scale GenAI services with high availability. - Optimized PostgreSQL and Redis systems to improve retrieval performance and reduce latency for AI applications. - Implemented observability pipelines (logging, monitoring, tracing) to ensure reliability and production readiness of AI systems.

Senior Software Engineer at Pratishthan Software Ventures Pvt. Ltd, Apr 2023 - May 2025 · 2 yrs 2 mos, Bangalore Urban, - Designed and implemented UKFPS and HKFPS payment services, including middleware and REST APIs for UK and HK banks on top of the Finacle platform. - Drove a critical NFR and performance initiative that reduced single-transaction latency from 8 seconds to 2 seconds by tuning database queries, caching, and messaging layers using Dynatrace and AWR insights. - Designed SWIFT payment architecture and integrated existing modules into a dedicated SWIFT microservice, ensuring scalability, reliability, and maintainability. - Worked on Mastercard integration for international transactions, collaborating with cross-functional teams to meet functional and non-functional requirements. - Enabled connection pooling in IBM MQ and configured Redis authentication/authorization, improving throughput, stability, and security for high-volume payment flows. - Created and reviewed technical design documents (LLD/HLD), analysed impact of new features on existing services, and handled production incidents and deployment-related issues.

Software Developer at TeckMines, Aug 2020 - Dec 2020 · 5 mos, Mumbai, - Owned end-to-end backend product development, delivering highly maintainable cloud services integrated across core business applications. - Designed and provisioned scalable cloud architecture on AWS, establishing decoupled messaging queues to support asynchronous communication and reliable data delivery. - Configured and managed on-site production deployments while successfully embedding MLOps practices into the core software delivery lifecycle.

Lead Software Engineer at Verdant Motors Pvt Ltd, Apr 2020 - Jan 2021 · 10 mos, Bangalore Urban, - Scaled and managed high-availability company web platforms and engineered secure internal admin portals to optimize operational workflows. - Architected and deployed production microservices on AWS, leveraging containerization to ensure seamless service integration and high reliability. - Designed and implemented an AWS-based IoT ingestion service enabling secure, low-latency communication patterns between edge devices and centralized servers

Education

Bachelor of Engineering - BE, Information Technology, Singhad institute of technology

Senior Secondary, Science, SBBG Inter College