.png){kind=logo}
Aisha Sartaj
Mid-level AI Engineer specializing in LLM systems, RAG, and MLOps
Connect with Aisha
Aisha 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
Built an LLM multi-agent “ingredient safety” analyzer for cosmetics that cuts consumer research time from ~20+ minutes to minutes, using LangGraph orchestration, hybrid retrieval (Qdrant + Tavily), and safety-focused critic validation (false rejections reduced ~30%→~8%). Also has research-internship experience building computer-vision pipelines to classify emerald color/clarity by translating gem-expert heuristics into quantitative model features.
Experience
Education
Key Strengths
- Built and deployed a multi-agent cosmetic ingredient safety analyzer with personalized recommendations
- Designed agent workflow with supervisor/research/analysis/critic roles and conditional routing in LangGraph
- Solved JS-rendered scraping blockers by adding rate limiting/retries and identifying need for Selenium
- Improved critic agent performance by refocusing validation on safety-critical issues (reduced false rejections from ~30% to ~8%)
- Pragmatic model selection based on cost/latency constraints (Gemini 2.0 Flash for ~20–30s responses)
- Implemented hybrid retrieval with Qdrant semantic search plus web-search fallback using similarity threshold (<0.7)
- Established reliability approach with measurable criteria (completeness, allergen detection as non-negotiable, latency) and iterative real-case testing
- Collaborated with non-technical domain experts to convert qualitative gemstone grading into quantitative CV classification criteria
Discover more candidates like Aisha
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent