Professional Overview
AI Engineer with 1.5 years building production RAG pipelines, LangGraph multi-agent systems, and fine-tuning LLMs (LoRA/QLoCA) on edge hardware. Shipped a LiteLLM gateway cutting costs 54% and an on-device SLM for Eli Lilly on Snapdragon 680. Springer-published on LLM adaptation. Open to remote roles.
Experience
AI Expertise
Skills
Employment Type
Description of Responsibilities
- - Built stateful 5-agent coaching system with LangGraph, Mem0 memory, and 25 too
- - Designed LiteLLM gateway routing OpenAI, Anthropic, and open-source models acr
- - Fine-tuned Qwen 0.6B/1.5B with LoRA for on-device diabetes guidance SLM on Sna
- - Built RAG pipelines with pgvector/Qdrant and async OCR/PDF processing streamed
- - Rebuilt 812-line rules-based nudge pipeline into decoupled DSPy GenAI architec
Key Achievements / KPIs
- - Cut LLM costs 54% by routing across OpenAI, Anthropic, and open-source
- - Reduced report processing from 40s to 15s with async OCR/PDF pipeline optimize
- - On-device SLM: 380MB, under 890ms latency, 25 tok/s, 98% OOD refusal accuracy
- - Springer-published on LLM adaptation (ICAAI 2025); promoted from intern to eng
Areas of Expertise
AI & Machine Learning Engineers
Design, train, and ship production ML models — from data pipelines to model inference at scale. Covers supervised learning, neural networks, LLM integration, and model optimisation.
Automation & AI Workflows
Build intelligent automation pipelines, integrate AI APIs into existing tools, and replace manual workflows with agentic AI systems.
AI Product & Strategy
Translate AI capabilities into product roadmaps, define success metrics, and drive adoption across engineering and business teams.
