Open to new opportunities

Hi, I'm Shaikh Faizan Ahmed

Generative AI Engineer, Software Engineer, Full Stack Developer, Agentic AI Systems

I specialize in building scalable production-grade AI platforms, LLM applications, RAG pipelines, and agentic AI systems. With a strong background in backend and observability engineering, I engineer robust systems that power real-time AI voice automation and advanced multi-agent orchestrations.

View ResumeSee My Work
Portrait of Shaikh Faizan Ahmed
Experience & Education

My Journey

Three years building production systems — from Fire OS observability at Amazon to multi-agent voice AI platforms.

  1. Full Stack Developer

    Vibrium AI

    Oct 2025 – Apr 2026Hyderabad, India
    • Designed and deployed a production-grade observability and analytics platform for AI voice agents using AWS Aurora RDS, Lambda and SQS, enabling real-time visibility into 100K+ daily call sessions, latency metrics, token usage and operational performance.
    • Built LLM-powered RAG systems using AWS Bedrock Knowledge Bases, Titan Embeddings and OpenSearch Vector Search, delivering low-latency knowledge retrieval for enterprise voice AI applications.
    • Developed a multi-agent orchestration framework with agent-to-agent transfer, agent-to-human escalation, contextual memory management and configurable function tools, deployed across multiple production environments.
    • Implemented scalable backend APIs, event-driven pipelines and AWS-based cloud infrastructure supporting conversational AI workflows, analytics processing and client cloud modernization initiatives.

  2. Software Development Engineer

    Amazon

    Jan 2024 – Jul 2025Bengaluru, India
    • Rebuilt a mission-critical internal log analysis platform, restoring 100% core functionality, improving system stability and successfully deploying it to production environments.
    • Engineered and deployed an ETL-based Low Memory Killer (LMK) reporting system using custom parsing logic and a dynamic JavaScript UI with AWS Glue, Athena and S3, improving log traceability by 3x.
    • Led a complete UI modernization of LogParrot, reducing internal troubleshooting time by approximately 25% and improving adoption across engineering teams.
    • Enhanced the PerfTracker observability platform, fixing 10+ legacy issues and introducing OOM scoring, memory KPIs and configurable measurement intervals for CPU, memory, perfstats, eMMC and job scheduler metrics.
    • Reduced logging noise by approximately 60% and improved debugging efficiency by 30% through performance and observability enhancements in the PerfTracker logging architecture.
    • Delivered critical Fire OS stability improvements, including configurable ANR timeouts, resolution of 2 major crash bugs in FOS 6 and granular tombstone diagnostics for crash analysis.

  3. Software Development Engineer

    Amploop

    Jul 2023 – Jan 2024Remote (Delhi, India)
    • Developed full-stack applications using Python, React.js, REST APIs and MySQL, contributing to the delivery of scalable production-ready software solutions.
    • Designed and implemented backend APIs and business logic modules, improving application responsiveness and reducing manual operational effort through workflow automation.
    • Resolved 20+ software defects through debugging, root-cause analysis and performance optimization, enhancing system reliability and user satisfaction.
    • Collaborated with product and engineering teams to translate business requirements into technical solutions.

  4. M.Tech in Computer Science and Engineering

    Indian Institute of Technology Jammu

    2023Jammu, India
    • Specialized in advanced computing concepts, distributed systems and modern software architectures.

  5. B.Tech in Computer Science and Engineering

    Jaipur National University

    2019Jaipur, India
    • Developed strong fundamentals in algorithms, data structures and computer programming.
Selected Work

Projects

Production AI systems, retrieval pipelines and research work — filter by focus area or search the stack.

Toolkit

Technical Skills

The stack behind the production AI systems, backend services and observability platforms above.

Programming Languages

6
  • PythonPrimary language across Amazon, Vibrium AI and every AI project here.
  • Java
  • JavaScriptUsed for the dynamic LMK reporting UI at Amazon and this site.
  • C
  • C++
  • HTML

Backend & Frameworks

7
  • FastAPI
  • Flask
  • Node.js
  • NumPy
  • Pandas
  • TensorFlow
  • PyTorchUsed for the motion-blur video super-resolution model.

Databases & Storage

5
  • MySQL
  • DynamoDB
  • Redis
  • AWS S3
  • Aurora RDSBacked the voice-agent analytics platform at Vibrium AI.

Cloud & DevOps

7
  • AWSEC2, S3, Lambda, Bedrock, Glue, Athena, CloudWatch, OpenSearch.
  • GCP
  • Docker
  • Linux
  • Jenkins
  • Git
  • Gerrit

GenAI / AI Stack

10
  • LLMs
  • RAG90%+ retrieval accuracy on the insurance document chatbot.
  • LangChain
  • Agentic AIMulti-agent orchestration with agent-to-agent and agent-to-human transfer.
  • LiveKitPowers the realtime voice agent on this site.
  • Vector Databases
  • EmbeddingsTitan and OpenAI embeddings for enterprise knowledge retrieval.
  • Prompt Engineering
  • HuggingFace
  • OpenAI API

Data & Observability

6
  • ETL PipelinesETL-based LMK reporting on AWS Glue, Athena and S3 at Amazon.
  • Kibana
  • OpenSearch
  • Log AnalyticsRebuilt Amazon’s internal log analysis platform to 100% functionality.
  • Performance MonitoringOOM scoring and memory KPIs in PerfTracker.
  • Distributed Logging
Credentials

Certifications

Verified credentials in generative AI, retrieval-augmented generation, machine learning and data analytics.