.png){kind=logo}
RD
Rakesh Deshalli Ravi
Mid-level Data Science & AI Engineer specializing in LLMs and cloud ML platforms
Los Angeles, CAData Science and AI Engineer6 years experienceMid-LevelHealthcareArtificial IntelligenceTechnology
ScreenedIdentity Verified
Connect with Rakesh
Rakesh 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 and deployed an LLM-powered mental health therapy assistant at AppHealth that segments users by stress level and delivers personalized, non-medical guidance. Implemented healthcare-focused safety guardrails (secondary LLM output filtering) and a multi-agent router workflow validated via statistical tests and therapist review, then scaled training/inference on AWS (EC2/Lambda/DynamoDB) with Kubernetes.
Experience
LLM Evaluation & Code Review— Mercor IntelligenceMercor
Computer Science AI/LLM TutorHandshake AI
Data Science and AI EngineerUpHealth AI
Consumer Data Analytics & AI InternBeats by Dre
Data Science and Teaching AssistantDePaul University
Data Science Specialist - Retail Space PlanningLowe's
Data ScientistAlpha Ventures
Data AnalystMurugan Construction Works
Education
DePaul Universitymaster, Data Science (2024)
Visvesvaraya Technological Universitybachelor, Engineering (2019)
Key Strengths
- Built and deployed a production mental-health therapy assistant using an LLM
- End-to-end data acquisition strategy (online research + interviews + therapist-sourced data) to create representative training data
- Iterative model improvement loop (testing, identifying failure modes, collecting more data, re-fine-tuning)
- Implemented safety controls to prevent medical advice (output barrier + secondary LLM output checker)
- Designed and evaluated a multi-agent workflow with a router agent; tested routing consistency across 50–150 similar queries
- Validated subjective outputs with therapists to ensure alignment with professional guidelines
- Scaled training/inference using AWS and Kubernetes; handled high API request volume via EC2 scaling
- Balanced quality vs cost by managing token limits through prompt shortening and fine-tuning
- Effective communication of LLM concepts and progress to non-technical stakeholders (therapists, CEO)
Discover more candidates like Rakesh
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent