.png){kind=logo}
Dinal Dholiya
Mid-level Full-Stack Engineer specializing in AI-powered and cloud-native systems
Connect with Dinal
Dinal 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
Product-minded engineer who has owned features end-to-end, including a full onboarding redesign that lifted completion ~25% and a production LLM/RAG report-generation system with strong guardrails (schema-constrained JSON, confidence gating, logging) and an automated eval/regression loop built from real user queries. Also built a scalable research data pipeline ingesting messy PDFs/JSON/CSVs with normalization, idempotent reruns, observability, and cost/latency tradeoffs.
Experience
Education
Key Strengths
- Owned end-to-end onboarding redesign (research, rebuild, launch, iterate)
- Improved onboarding completion ~25% by reducing upfront friction
- Pragmatic MVP tradeoffs (core path first; defer rare edge cases)
- Production RAG system design (ingestion → embeddings → retrieval → structured generation)
- Strong reliability guardrails (context restriction, JSON validation + retries, confidence thresholds, full logging)
- Built evaluation loop from production queries with automated regression tests
- Used eval findings to add confidence gate when retrieval similarity was low (reduced overconfident answers)
- Designed scalable messy-data pipeline with normalization, idempotency, observability, and staged processing tradeoffs
Discover more candidates like Dinal
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent