Reval LogoFind More Talent
WL

winston lo

Junior Software Engineer specializing in AI agents, RAG, and full-stack development

RemoteSoftware Engineer2 years experienceJuniorArtificial IntelligenceAutomotiveGovernment
ScreenedIdentity Verified

Connect with winston

winston 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

Backend engineer who built and iterated a secure, multi-tenant RAG system over a large document corpus, emphasizing strict RBAC/ACL isolation, hybrid retrieval (vector+keyword), reranking, and strong observability to balance relevance, latency, and cost. Also led production refactors/migrations using strangler + feature flags/dual writes and has experience catching subtle real-world failure modes (including in a sensor calibration optimization pipeline).

Experience

Software EngineerTresle AI
Software Engineer (Contract)Lucid Motors
Software Engineer InternSan Francisco Police Department (SFPD)
Software EngineerFlowNow
Software Engineer (Contract)Bentley Systems

Education

University of California, Berkeleybachelor, Computer Science and Data Science (2026)

Key Strengths

  • Designed secure RAG backend with early ACL filtering and hybrid retrieval (vector + keyword) plus reranking
  • Strong multi-tenant data isolation via retrieval-time filtering and centralized policy evaluation
  • Balances relevance, latency, and LLM/infra cost using candidate set limiting, chunking strategy, and caching
  • Security-first mindset with access-control audits, detailed retrieval decision logging, and cross-tenant test coverage
  • API platform engineering in FastAPI: versioned contracts, backward compatibility, deprecation strategy, and contract tests
  • Led low-risk migrations using strangler pattern, feature flags, dual writes, parallel output validation, and canary rollouts
  • Deep observability practice (metrics, tracing, structured logs) to diagnose slow dependencies and regressions
  • Proactively finds hidden failure modes (e.g., false local minima in calibration optimization) and adds scenario-based validation

Discover more candidates like winston

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

Search Talent

Connect with winston

winston 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

PythonJavaJavaScriptTypeScriptSQLHTMLCSSSwiftPine ScriptAWSAWS BedrockAWS Bedrock AgentCoreAWS S3AWS LambdaAWS IAM