Abdeali Patanwala

Software Engineer

Seattle, Washington, United States7 yrs 2 mos experience
AI EnabledAI ML Practitioner

Key Highlights

  • Expert in large-scale distributed systems design.
  • Proven track record in AI infrastructure optimization.
  • Strong background in cloud-based solutions and microservices.
Stackforce AI infers this person is a Backend-focused Software Engineer with expertise in AI and Cloud Computing.

Contact

Skills

Core Skills

Large-scale Distributed SystemsAi WorkloadsDistributed SystemsCloud SolutionsScalable SystemsBackend Development

Other Skills

AI InfrastructureTriton-MTIAPyTorchPerformance AnalysisAPIsCloud DeploymentPredictive MonitoringDynamoDBLambdaAWS FargateMicroservicesPythonAWSOracle Database.NET Framework

About

As an experienced software engineer with a background in computer networking, I have a proven track record of working on large-scale systems. With a Master of Science degree in Computer Science from Boston University, I bring strong engineering skills and a passion for developing innovative solutions that meet the needs of today's ever-evolving technology landscape. I am committed to delivering high-quality work that meets or exceeds customer expectations, and I thrive in fast-paced, dynamic environments where teamwork and collaboration are key.

Experience

7 yrs 2 mos
Total Experience
2 yrs
Average Tenure
1 yr 2 mos
Current Experience

Meta

Software Engineer at Meta - AI Infra

Mar 2025Present · 1 yr 2 mos · Bellevue, Washington, United States · On-site

  • Joined the AI Infra team as part of Meta’s AI Training and Inference Accelerator (MTIA) initiative, working on cutting-edge custom silicon designed for AI workloads.
  • Developing high-performance compute kernels using Triton-MTIA, optimizing PyTorch operators for ranking and recommendation models.
  • Collaborating closely with hardware engineers to refine the next-gen MTIA chips, achieving a 3x performance increase over previous models.
  • Spearheading the integration of AI accelerators across Meta’s data centers, ensuring seamless deployment and compatibility with existing systems.
  • Conducting extensive performance analysis to identify bottlenecks in AI infrastructure, implementing optimizations to enhance compute efficiency and throughput.
  • Collaborate with hardware and software teams to refine the Meta Training and Inference Accelerator, achieving a 3x performance boost in ranking and recommendation models.
  • Develop and implement high-performance compute kernels using Triton-MTIA, enhancing the efficiency of PyTorch operators.
  • Integrate AI accelerators across Meta’s data centers, ensuring smooth deployment and compatibility with existing infrastructure.
AI InfrastructureTriton-MTIAPyTorchPerformance AnalysisLarge-Scale Distributed SystemsAI Workloads

Microsoft

Senior Software Engineer

Apr 2022Mar 2025 · 2 yrs 11 mos · Redmond, Washington, United States · On-site

  • Led the design and implementation of distributed systems in Hermes, delivering scalable solutions for millions of devices.
  • Built APIs and SDKs for device management, streamlining remote upgrades and large-scale account offboarding.
  • Implemented cloud deployment pipelines, incorporating automated monitoring to minimize downtime and optimize performance.
  • Developed predictive monitoring systems to identify and resolve potential service disruptions ahead of customer impact.
  • Collaborated across teams to refine system architectures for greater resiliency and maintainability.
Distributed SystemsAPIsCloud DeploymentPredictive MonitoringCloud Solutions

Amazon

Software Development Engineer

Apr 2020Apr 2022 · 2 yrs · Seattle, Washington, United States · On-site

  • Designed a scalable link-checking system using DynamoDB and Lambda, processing millions of records daily with optimized data handling.
  • Developed a multithreaded framework for parsing robots.txt files, improving content processing efficiency.
  • Integrated AWS Fargate for distributed load testing, facilitating large-scale content verification during migration.
DynamoDBLambdaAWS FargateCloud SolutionsScalable Systems

Ramp

Back End Developer

Mar 2019Apr 2020 · 1 yr 1 mo · Boston, Massachusetts

  • Developed backend microservices for cloud-based architectures, improving data processing workflows.
  • Implemented a Python-based test automation framework on AWS, reducing testing cycles by 30% and streamlining validation processes.
MicroservicesPythonAWSBackend DevelopmentCloud Solutions

Education

Boston University

Master of Science - MS — Computer Science

Jan 2017Jan 2019

Rajiv Gandhi Prodyogiki Vishwavidyalaya

Bachelor of Engineering - BE — Information Technology

Jan 2013Jan 2017

Stackforce found 100+ more professionals with Large-scale Distributed Systems & Ai Workloads

Explore similar profiles based on matching skills and experience