Shahid Afridi
@shahidafridi2
AI Research Associate specializing in LLM and web-agent evaluation, prompt engineering, and robust safety testing.
What I'm looking for
I’m an AI Research Associate with 1 year of hands-on experience contributing to production AI agent training pipelines for a major cloud provider’s web browser agent. My core work spans LLM agent evaluation, Chain-of-Thought trajectory annotation, and simulated environment testing, and I was promoted to Technical Research Associate within 3 months.
I lead evaluation efforts by detecting hallucination, reward hacking, and prompt injection/leakage, and by validating Human-in-the-Loop checkpoints using internal evaluation tooling. I also define JSON schemas within prompts for structured outputs, supervised 2–3 Research Associates, and onboarded 3–4 joiners on evaluation protocols—actively building toward an AI Engineer role.
Experience
Work history, roles, and key accomplishments
Led web-agent trajectory data collection by authoring multi-step task prompts and capturing screenshot-based step-level Chain-of-Thought annotations to train GUI-based LLM agents. Contributed to production web browser agent evaluation across synthetic web gyms, performing multimodal checks for hallucinations, prompt leakage, reward hacking, and HITL checkpoints; supervised 2–3 associates and onboa
Collected web-agent trajectory datasets by executing prompt-driven UI interactions on live websites and writing step-level Chain-of-Thought annotations for screenshot-based action sequencing. Evaluated model outputs for correctness, instruction adherence, reasoning quality, and safety compliance, delivering consistently high-accuracy results that led to promotion within 3 months.
Education
Degrees, certifications, and relevant coursework
REVA University
Bachelor of Technology (B.Tech), Electrical and Computer Engineering
Grade: CGPA: 7.7/10
Completed a B.Tech in Electrical and Computer Engineering at REVA University in 2024. Achieved a CGPA of 7.7/10.
Availability
Location
Authorized to work in
Job categories
Interested in hiring Shahid?
You can contact Shahid and 90k+ other talented remote workers on Himalayas.
Message ShahidGet matched with your dream remote job
Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!
