Neerav Jha
Open to work1 years experienceSoftware Engineer
Software Engineer specializing in LLM-orchestrated conversational AI and backend systems.
Standing Rank
Rank Not Available
Developer Badges
No badges earned yet
Skills & Technologies
26 skillsWork Experience
Associate Software Engineer
Yellow.ai
- Built and productionized multi-channel conversational AI systems (chat & voice) using RAG pipelines and LLM orchestration (function calling, tool routing, caching), improving response latency and containment rate.
- Designed and shipped the platform's first ServiceNow integration (OAuth 2.0, event-driven sync, resilient REST APIs), improving API reliability and throughput while reducing mean time to recovery (MTTR).
- Added performance instrumentation across orchestration services to surface latency and reliability regressions before they impacted customers.
Python Developer Intern (Backend Engineering)
Munsow Technologies
- Built backend services (Flask, MongoDB) for an AI-powered flashcard learning platform, integrating the OpenAI API for automated content generation; implemented RBAC and RESTful APIs supporting 1,000+ registered users and 150+ concurrent sessions.
- Owned API testing, debugging, and performance validation using Postman, ensuring reliable request handling and consistent data across the platform.
Projects
LLM Gateway — Multi-Provider LLM Routing Gateway
View Project- Built and deployed an OpenAI-compatible multi-provider LLM gateway with automatic fallback, two-layer caching (exact-match + semantic via vector similarity), sliding-window rate limiting, and cost tracking; fixed a connection-pooling bottleneck that cut p50 latency from 3.8s to 473ms.
- Implemented semantic caching (embeddings + cosine similarity) with a threshold calibrated from measured data (paraphrases ~0.89–0.92 vs. unrelated ~0.56), serving cached answers for reworded prompts.
taskq — Distributed Task Queue
View Project- Built a distributed task queue with priority scheduling, idempotent enqueue, exponential-backoff retries with dead-letter handling, and backpressure (503 + Retry-After at queue depth cap).
- Designed job leasing + heartbeat-based failure detection so a hard-killed worker's job is automatically rescued by another worker within seconds — verified via a live kill-worker test; load-tested at ~520 enqueue req/s locally (p50 28ms).
Leaderboard Standings
Leaderboard Position Pending
Global test scores, peer standing percentiles, and algorithm leaderboard ranks are updated dynamically.
Assessment Highlights
Assessments Not Completed
Coding evaluations, system assessment results, and conceptual score badges will appear here after taking a test.
AI Collaboration Score
AI Collaboration Score Pending
Developer coding behavior, assistant cooperation, and AI pair-programming indicators are evaluated during live coding sessions.
Role Compatibility Profile
Role Compatibility Analysis Pending
Custom matching reports, candidate role compatibility percentiles, and core engineer strength profiles are processed once conceptual code screenings are complete.
Achievements
Problem Solving Achievements
1100+ LeetCode problems solved; 5-star Python rating on HackerRank; 1000+ problems solved across LeetCode, HackerRank, and GeeksforGeeks.
About Details
Professional Bio
Software Engineer with production experience building LLM-orchestrated conversational AI systems and backend integrations at enterprise scale. Skilled in RAG pipelines, tool/function-calling orchestration, and resilient REST API design.
Bachelor of Technology in Computer Science and Engineering
HNB Garhwal University ( - 2024)