Senior AI Engineer and AI Tech Lead with 3+ years of experience architecting and shipping production systems that combine high-performance backend engineering with applied AI product development. Currently leading a cross-functional team of 10 engineers at Simplyphi, a UK-based product startup, spanning AI engineering and full-stack development.

I specialize in taking AI products from concept to production — designing LLM-powered systems, RAG pipelines, and multi-agent architectures, while also owning the underlying distributed systems, microservices, and scalable APIs that make them reliable in the real world. I bridge the gap between "AI that works in a demo" and "AI that works in production."

• Leading a cross-functional team of 10 engineers across AI Engineering and Full-Stack Development, owning delivery from architecture through production release.
• Own technical architecture and project planning for AI and full-stack initiatives — setting technical direction, scoping systems, and de-risking delivery timelines.
• Mentor and upskill developers through structured code reviews, architecture walkthroughs, and pairing — raising the team's engineering bar on clean architecture, testing, and AI system design.
• Drive AI product development end-to-end, from ideation and stakeholder alignment through design, implementation, evaluation, and deployment.
• Champion engineering best practices — SOLID principles, clean architecture, dependency injection, and repository patterns — across both AI and traditional backend services.
• Act as the technical bridge between product stakeholders and engineering, translating business requirements into system designs and AI workflows.

LLMs & Generative AI LLM Application Development · Prompt Engineering · Function Calling · Structured Output Generation · Fine-Tuning Concepts · Evaluation Frameworks · Guardrails & AI Safety · AI Observability

Retrieval & Knowledge Systems Retrieval-Augmented Generation (RAG) · Semantic Search · Embedding Models · Vector Databases (Pinecone, Weaviate, ChromaDB, FAISS) · Knowledge Graph Integration

Agentic Systems AI Agents · Multi-Agent Systems · Model Context Protocol (MCP) · LangChain · LangGraph · LlamaIndex · AI Workflow Automation

Model Providers & Platforms OpenAI APIs · Anthropic Claude APIs · Google Gemini APIs · Hugging Face Transformers

I design AI systems the way I design backend systems — modular, observable, and built to handle failure gracefully, not just to work on the happy path.

Frontend React.js · Next.js · Angular · TypeScript · JavaScript

Backend Go (Golang) · C# / .NET · Node.js · Express.js · Python · FastAPI

APIs & Architecture REST APIs · GraphQL · Microservices · System Design · Scalable & Distributed Architecture · Event-Driven Design

Data & Infrastructure PostgreSQL · MySQL · MongoDB · Redis · Docker · Kubernetes · AWS / Azure / GCP · CI/CD

Core Backend Strengths

• High-concurrency services in Go using goroutines, channels, and worker pools
• Clean Architecture, SOLID principles, and modular, testable system design
• Layered architecture, dependency injection, and repository patterns
• Middleware-based authentication and API security

Architected an AI-powered digital health journal that extracts structured insights from medical reports using AWS Textract and Bedrock, built on a scalable cloud-native stack. Go · Angular · AWS Bedrock · AWS Textract · PostgreSQL

Built a next-generation AI conversation platform unifying voice and chat into a single seamless experience, using NLP and text-to-speech to automate real-time, human-like communication at scale. Go · Docker · Microservices · WebSockets · NLP · Text-to-Speech

Developed a Python-based AI automation tool that streamlines repetitive job-search and application workflows on the Naukri job portal. Python · AI · Automation

Designed and delivered 4–5 production Retrieval-Augmented Generation (RAG) systems at Simplyphi, integrating LLMs with internal knowledge bases, documents, and third-party APIs to automate research, support, and knowledge-retrieval workflows for business stakeholders. RAG · LLMs · Vector Databases · LangChain · Go · Microservices

Fill in with real, verifiable numbers — even modest, specific metrics read as far more credible than vague claims.

• Reduced [system/process] latency by [X]% through [specific optimization].
• Led delivery of [X] production releases across AI and full-stack initiatives with zero critical rollbacks.
• Mentored [X] engineers, with [X] promoted or advanced in scope during that time.
• Designed and shipped an AI system serving [X] end users / [X] requests per day.