Reval LogoFind More Talent
AE

Ashish Ernest Jeldi

Senior Data Scientist specializing in LLMs, agentic AI, and MLOps

Boston, MAData Science Advisor6 years experienceSeniorTechnologyEnterprise SoftwareArtificial Intelligence
ScreenedReferences VerifiedIdentity VerifiedStrongly Recommended

Connect with Ashish

Ashish 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 shipped a production agentic LLM tool that helps internal teams update technical product whitepapers using plain-language edit requests, with strong guardrails (citations, verification, refusal/clarify flows) to reduce hallucinations and maintain compliance. Experienced taking LLM workflows from rapid LangChain prototypes to more predictable, debuggable LangGraph agent graphs, and orchestrating end-to-end ingestion/embedding/indexing/eval/deploy pipelines with Kubeflow.

Experience

Data Science AdvisorDell Technologies
Data Science InternThe Clorox Company
Machine Learning Engineer InternToken Metrics
Data ScientistAccenture Services Private Limited

Education

Northeastern University, Khoury College of Computer Sciencesmaster, Artificial Intelligence (2022)
Northwestern University, McCormick School of Engineeringmaster, Computer Engineering (2021)

Key Strengths

  • Built and deployed production agentic LLM system for technical whitepaper revision via natural-language change requests
  • Strong grounding strategy: retrieval-coupled generation with citation-required prompts and verification of claims against sources
  • Performance/cost optimization via dynamic indexing (re-embed only changed sections)
  • Long-document and structure-preserving generation (headings/tables/format constraints) for enterprise documents
  • Production reliability engineering for LLM apps (confidence thresholds, clarifying questions/refusals, fallbacks, monitoring)
  • Scaled orchestration from LangChain to LangGraph for explicit stateful control flow, debugging, retries, and conditional paths
  • Rigorous evaluation approach: layered testing (unit/golden/adversarial/replay) plus offline and online metrics with canary/A-B releases
  • Effective collaboration with non-technical stakeholders using transparent UX patterns (diff output, citations) and iterative demos

Reference Highlights

Strongly Recommended
  • Proactive in researching state-of-the-art techniques
  • Brings new ideas/techniques to the team
  • Strong system design contributions (agents, workflow, memory schema)
  • Takes the lead and acts in the team’s best interest
  • Excellent stakeholder management
  • Eloquent communicator
  • Exceptional at simplifying complex concepts for non-technical audiences
  • Helps users/testers understand and effectively test the application
  • Integral in gathering feedback and addressing product gaps
  • Very knowledgeable in his field
  • Excited and keen to contribute
  • Strong communication skills
  • Able to work with people across various domains
  • Translates technical concepts into clear, non-jargon language
  • Helps align on problems and solutions with diverse stakeholders
  • Contributed strong ideas leading to excellent project remarks
  • Effective at explaining projects in depth to professors
  • Supportive teammate who brings others up to speed

Discover more candidates like Ashish

Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.

Search Talent

Connect with Ashish

Ashish 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?

Contact

candidate@example.com(555) 123-4567LinkedIn Profile
Sign up to view

Languages

English

Skills

PythonJavaSQLCC++JavaScriptD3.jsNode.jsRNumPyPandasScikit-learnSeabornMicrosoft AzureAWS