ML engineer specializing in agentic workflows and LLM applications.
3+ years of experience designing intelligent systems, deploying models, and integrating cloud-native backends. Focused on LLM-powered agents, semantic search, and real-time data using LangChain, LangGraph, and FastAPI.
ML engineer with 3+ years building end-to-end AI solutions—from data ingestion and model training to production deployment. Experienced across ML research, infrastructure, and backend development with a strong focus on LLM agents, semantic retrieval, and modular reasoning. I enjoy translating complex problems into scalable, real-world applications.
Jul 2024 – Present
Developed high-volume SQL queries and streaming pipelines, automating ETL across cloud datasets to deliver reliable analytics in near real time.
Sep 2024 – Jul 2024
Fine-tuned DNABERT and HyenaDNA models with LoRA and soft prompting, reaching 94%+ accuracy while cutting iteration cycles by 40%.
Jun 2023 – May 2024
Orchestrated genomic ETL pipelines with Airflow and Glue, automating model retraining to boost data availability 50% and cut manual effort 40%.
Jul 2021 – Dec 2022
Migrated batch jobs to Kafka/Spark streaming and redesigned Snowflake schemas, cutting query latency 40% and accelerating deployments by 25%.
Graph-based LLM chatbot enabling multi-agent conversations with LangGraph.
Custom LLM agent achieving 80%+ step accuracy for mobile UI task automation.
Proxy-tuned BERT models improving NER F1-score by 8% while cutting compute 70%.
Download my full resume or view a condensed version.