.png){kind=logo}
EH
Ebtesam Haque
Mid-level AI Researcher specializing in LLMs, developer tools, and human-centered AI
McLean, VAGRADUATE RESEARCH ASSISTANT4 years experienceMid-LevelArtificial IntelligenceEducationHealthcare
ScreenedIdentity Verified
Connect with Ebtesam
Ebtesam already has a relationship with Reval, so a warm intro from us gets a much better response than cold outreach.
Recommended
Already have an account?
About
Research-focused AI engineer who built an agentic pipeline to automatically extract Sphinx-based API documentation/changelogs and generate synthetic tasks for a dynamic LLM code benchmark targeting real-world API evolution and deprecations. Experienced with multi-agent orchestration (AutoGen, LangChain, CrewAI) and rigorous evaluation methods, and has prior multi-agent work from a Microsoft Research internship.
Experience
GRADUATE RESEARCH ASSISTANTSchar School of Policy and Government, George Mason University
GRADUATE RESEARCH ASSISTANTInspired Lab, George Mason University
RESEARCH INTERNMicrosoft Research
NSF RESEARCH TRAINEECenter for Adaptive Systems of Brain Body Systems, George Mason University
Education
George Mason Universitymaster, Computer Science (2025)
George Mason Universitydoctorate, Computer Science
Key Strengths
- Built an MVP pipeline to generate dynamic LLM benchmarks from evolving API docs/changelogs
- Deep practical understanding of deprecated API behavior and how training-data distributions affect LLM codegen
- Hands-on multi-agent orchestration experience (AutoGen/LangChain/CrewAI) including pre-framework scratch implementations
- Strong evaluation mindset: combines offline benchmarks with qualitative user feedback and iterative test-case expansion
- Pragmatic scoping and architecture decisions (narrowed to Sphinx; leveraged .inv structure; added validation step to enforce constraints)
- Produced measurable findings (Gemini-2.5-Flash generated deprecated matplotlib behavior ~40% of the time)
Discover more candidates like Ebtesam
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent