Shahid Afridi

Software Engineer

Bengaluru, Karnataka, India11 mos experience

Most Likely To SwitchAI ML Practitioner

Key Highlights

Expert in AI evaluation and data analysis.
Proven track record in improving AI output quality.
Strong communication skills in team environments.

Stackforce AI infers this person is a skilled AI evaluator with a focus on operational efficiency.

Contact

Skills

Core Skills

Ai EvaluationData AnalysisOperational Support

Other Skills

LLM workflowsquality checkstechnical documentationteam communicationprompt designquality assurancestructured analysisprompt testingdocumentationprocess documentation

About

Uncovering hidden insights in complex datasets using Python, SQL, and data visualization.Passionate about leveraging data to streamline operations and improve efficiency.

Experience

11 mos

Total Experience

5 mos

Average Tenure

8 mos

Current Experience

Keywords studios

2 roles

Technical Research Associate – AI

Promoted

Oct 2025 – Present · 8 mos · Bengaluru, Karnataka, India · On-site

Technically evaluated agentic AI systems and LLM-based workflows for correctness, consistency, and task completion.
Designed, tested, and refined structured prompts to improve AI agent reliability and output quality.
Performed quality checks (QC) on Research Associate deliverables to ensure adherence to evaluation guidelines and accuracy standards.
Reviewed AI output evaluations completed by team members and validated findings before final submission.
Acted as a point of contact for resolving technical doubts and clarifying evaluation criteria for Research Associates.
Guided and supported team members based on project updates and instructions received from senior stakeholders.
Communicated task updates, feedback, and priority changes to the team to ensure smooth project execution.
Analyzed AI outputs to identify failure modes, hallucinations, and edge cases across complex task flows.
Documented technical and quality insights to support AI system optimization and continuous improvement.
Collaborated with AI, QA, and research teams on evaluation frameworks, benchmarking, and reporting.

AI evaluationLLM workflowsquality checkstechnical documentationteam communicationdata analysis

Research Associate AI

Jul 2025 – Sep 2025 · 2 mos · Bengaluru, Karnataka, India · On-site

Evaluated AI systems and large language model (LLM) outputs for accuracy, relevance, and task completion.
Performed structured analysis of AI-generated responses across multiple real-world use cases.
Assisted in prompt testing and refinement to improve response quality and consistency.
Identified errors, edge cases, and failure patterns in AI outputs.
Documented evaluation findings to support AI quality improvement initiatives.
Worked closely with QA and research teams to follow evaluation guidelines and benchmarks.

AI evaluationstructured analysisprompt testingdocumentation

Resource pro

Associate – Service Delivery Unit

Mar 2025 – Jun 2025 · 3 mos · Bengaluru, Karnataka, India

Supported operational and quality-driven processes by following defined workflows and SLAs.
Performed quality checks and validation of assigned tasks to ensure accuracy and compliance.
Documented process updates and communicated status to relevant stakeholders.
Developed strong attention to detail, process discipline, and professional communication skills.

operational supportquality assuranceprocess documentation