Sarita Singh

As an AI Engineer, I am driven by a deep ambition and determination to master complex challenges, always applying a logical and structured approach to problem-solving. I thrive on collaborating with others to develop innovative, pragmatic solutions that push the boundaries of technology and deliver tangible impact.

Experience

AI Engineer

Intel Corporation · Oct 2023 – Present

Not yet confirmed

• GenAI Agentic Debug Tool: Architected a multi-agent agentic harness (GPT-4 + Microsoft AutoGen, 5 agents: RAG, RCA, image/text analysis, summarizer) delivering net-new GenAI root-cause analysis at >80% accuracy; adopted by ~100 engineers across 4 teams (BIOS, SysDebug, integration, validation), cutting a ~500-ticket backlog by ~20%/week.
• Deployed the GPT-4 backend on Azure OpenAI in a secure hybrid-cloud topology (VNet, private endpoints, internal DNS); built the RAG pipeline over debug logs/BKMs and a RESTful server-client architecture integrating JIRA/HSDE APIs and Jenkins CI.
• Copilot Platform Debug Agent: Designed and shipped an inner-source GitHub Copilot agent + skills library delivering AI-powered root-cause analysis via a custom agentic harness that orchestrates 4 MCP server integrations (HSDE, JIRA, Wiki, co-design) for autonomous ticket fetching, similarity search, and BKM lookup across Intel 10 platform families.
• Cut the 10-engineer SysDebug team's platform-ticket backlog by 35%; built a curated BKM knowledge base (automated OneNote/wiki -> Markdown pipeline) with single-command, zero-admin onboarding.
• Smart IFWI (Integrated Firmware Image) Regression Engine: Sole owner of full lifecycle architected a Python tool (GUI + CLI) for firmware regression isolation with a Claude AI advisor correlating defect-ticket context with binary diffs to surface root-cause components.
• Reduced investigation time from ~109 min to ~6 min (100+ engineering hours/quarter); shipped as a zero-dependency Windows .exe with concurrent HSDE/Jira ingestion via MCP, adopted across 5 teams (50+ engineers).
• Automated PythonSV Installer: Windows tool provisioning Intel PythonSV debug environments across 6 platforms; cut setup from ~30 to ~5 min (83%) with a two-tier Claude recovery pipeline, deployed organization-wide.
• Deep Learning Log Anomaly Detection: Trained a CNN-LSTM model at 99.19% accuracy on an imbalanced dataset for first-level log triage, saving the SysDebug team ~8 engineering hours/day; auto-generates reports with linked HSDE/Jira defect IDs.
• Deployed as a Dockerized Flask app behind NGINX/SSL with MongoDB and Docker CI/CD.

Software Developer

Intel Corporation · Oct 2023 – Present

Not yet confirmed

• Built a GenAI agentic tool (Python, AutoGen, OpenAI API, MySQL, REST API, RAG, JIRA/HSDE, Jenkins) for automated debugging and log analysis, featuring collaborative agents, modular architecture, and multithreading for scalable ticket resolution.
• Achieved 80%+ confidence in component identification and documented workflows with Mermaid diagrams.
• Also developed a deep learning log analysis tool (Python, TensorFlow, Keras, Flask, MongoDB, Docker) with a CNN-LSTM model (99.19% accuracy), data augmentation, and a Flask web app for auto-triage and user management.

Software Developer Intern

Intel Corporation · Jul 2022 – Jun 2023

Not yet confirmed

• • Worked on FlexRAN fronthaul library (O-RAN 7.2x split).
• Contributed to two releases of the software.
• • Worked on the consumers facing bugs related to DPDK memory and several sample-app related issues like,
• supporting bbupool + multi numerology, adding dual socket configurationsetc.
• • Added PM counter check for PRACH packets when they had missed a timing window.
• • Added support for virtual Numerology= 4.

Software Development Engineer Intern

Google Summer of Code · May 2021 – Aug 2021

Not yet confirmed

• Selected for GSoC 2021 (~8% acceptance) to integrate ScanCode into FOSSology; built a C++ IPC wrapper wired into PostgreSQL and PHP/Twig UI for SPDX license detection PR merged into main repo (link).

Student Developer

Google Summer of Code · May 2021 – Aug 2021

Not yet confirmed

• • Contributed and worked on the FOSSology project.
• The task was to integrate a ScanCode Toolkit(another
• open-source project) License and Copyright scanner into the FOSSology Project.
• • The project included writing a C++ wrapper around ScanCode Python scripts and integrating it in the
• FOSSology PostgreSQL database and UI written in PHP and Twig.
• • The integration can scan for licenses, copyright and store the results in the FOSSology database.