ML Performance Engineer at AWS optimizing large language model inference on custom ML accelerators. 6+ years of experience spanning ML systems, performance optimization, and distributed systems. Proficient in ML frameworks, profiling, collective communication, distributed inference, kernel-level optimization, and hardware-level systems analysis.
Experience
ML Performance Engineer
January 2025 – PresentAmazon Web Services
- Own performance optimization of large language model inference on Trainium, AWS' custom ML accelerators, spanning profiling and roofline analysis, kernel-level work on attention, MoE, MLP, KV-cache management, and sharding-strategy analysis (tensor / data / expert parallelism, etc.)
- Drive deep dives into accelerator hardware features through targeted microbenchmarking, characterizing performance limits and surfacing gaps that drove microcode and ISA changes across teams
- Lead the design of mixed-sequence-length support in the attention kernel, defining the required framework- and kernel-level changes
- Led the design and delivery of end-to-end benchmarking and profiling infrastructure for monitoring inference accuracy, latency, throughput, and cost across model architectures and serving configurations; partnered across teams to define its interface and mentored junior engineers through implementation
- Lead a recurring paper reading group to grow the team's knowledge of ML systems research and emerging work
Software Engineer
August 2021 – December 2024Amazon
- Developed a real-time distributed platform and API for ad measurement using AWS CDK, EC2/ECS, ELB and Elasticache
- Led system and feature launches end-to-end: capacity planning, load testing, data correctness validation, dashboards, monitoring, alarming, and regression detection
- Investigated and root-caused system-wide outages and accuracy issues impacting advertiser data
- Worked cross-functionally with Product Management to develop new features, perform data investigations, address Advertiser's concerns and explain business logic
Data Engineer
February 2019 – August 2021Royal Bank of Canada
- Designed and built a multi-component streaming and cache-based application for address cleansing, achieving 30% cost reduction over the prior pipeline
- Built end-to-end metrics collection, monitoring, and reporting infrastructure across core production components
- Developed ETL pipelines with Spark and Airflow combining multiple data sources to back an internal API
Research
Attentional Guidance in Visual Search
2017Centre for Vision Research, York University, supervised by Prof. James Elder
- Conducted original research on the interaction between endogenous (top-down) and exogenous (bottom-up) attentional cues in visual search
- Designed a probabilistic cueing paradigm to measure how prior cue reliability shapes attentional guidance during visual search tasks
- Developed serial, parallel, and hybrid computational models of attentional guidance and evaluated them against human behavioural data
Lassonde Undergraduate Research Award
2016, 2017York University
Skills & Technologies
ML & Systems: NKI (Neuron Kernel Interface), AWS Neuron SDK, vLLM, PyTorch
Performance & Hardware: AWS Trainium / Inferentia, kernel optimization, roofline analysis, collective communication, distributed inference, profiling
Languages: Python, Scala, Java, SQL, TypeScript
Data & Infrastructure: Apache Spark, Airflow, AWS CDK, Pandas, NumPy, Elasticsearch, EMR, EC2, S3, SQS, CloudWatch, DynamoDB, Aurora
Education
York University
B.Sc., Honours in Computer Science