.png){kind=logo}
Yashwanth J
Mid-level Software Engineer specializing in AI/ML and full-stack systems
Connect with Yashwanth
Yashwanth 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
Engineer with Apple experience building LLM-powered internal workflow orchestration systems using Python, LangGraph, FastAPI, Redis, vector search, and Kubernetes. Stands out for a highly pragmatic, production-focused approach to agentic systems: deterministic state management, strong guardrails, observability, and human review for high-risk actions.
Find your next great hire
Our AI agents source, screen, and vet candidates for your open roles. Get qualified candidates within 48 hours.
Key Strengths
- Built AI workflow orchestration systems for internal Apple workflows
- Strong deterministic agent orchestration design
- Deep focus on guardrails, validation, and human-in-the-loop safety
- Production-grade failure handling with retries, timeouts, fallback paths, and escalation
- Robust observability using logging, metrics, Prometheus, and OpenTelemetry
- Careful reviewer of AI-generated code for security, scalability, and edge cases
- Experience improving agent reliability through prompt constraints and tool-selection controls
- Pragmatic framework evaluation for production readiness
- Owned end-to-end real-time fraud/transaction monitoring feature (design → build → launch → iterate)
- Scaled system processing 50,000+ daily transactions with security and performance focus
- Reduced system latency by 25% via optimized SQL and Hibernate caching
- Implemented OAuth 2.0 + RBAC to meet PCI DSS compliance requirements
- Post-launch iteration driven by user feedback: richer alerts and filtering to prioritize cases
- Reduced false positives by refining detection algorithms and adding validation rules
- Improved dashboard load times by 30%
- Reduced manual investigation time by 40% through workflow/product improvements
- Built scalable ETL pipeline for messy multi-source financial data with schema validation and edge-case handling
- Improved data integrity from 87% to 99% and maintained 99.8% uptime with observability (ELK) and reliability patterns (retries, DLQ)
- Designed latency/cost tradeoffs using batching for non-critical data and real-time processing for high-priority transactions
Like what you see? We'll introduce you to Yashwanth directly.
Experience
Education
Awards
Skills
Languages
Certifications
Browse Similar
Interested in Yashwanth?
We'll personally introduce you - no strings attached.
Build your dream team with Reval
Our AI agents source, screen, and vet candidates for your open roles. Get qualified, high-intent candidates on your desk within 48 hours.
Discover more candidates like Yashwanth
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent