Vetted JSON Professionals

“Built and shipped a production LLM hallucination detection and monitoring pipeline using semantic-level entropy (embedding-clustered multi-generation variance) to flag unreliable outputs in downstream automation. Implemented a scalable async architecture (FastAPI + Docker + Redis/Celery) with strong observability (structured logs + PostgreSQL) and developed evaluation loops combining controlled prompts and human review; also partnered with non-technical stakeholders on AI-driven form validation/document processing.”

“Built and productionized a real-time social-media sentiment analysis system used by a marketing team to monitor brand/campaign performance. Experienced in orchestrating LLM workflows with LangChain (validation → prompting → parsing → post-processing), plus monitoring, retraining, and RAG-style retrieval using embeddings/vector stores to keep outputs reliable over time.”

“Backend-focused engineer with experience spanning research and healthcare: owned a Python/SQL data pipeline that transformed vulnerability-fix code data from SQLite into model-ready JSON for LLM analysis. Also deployed Dockerized Spring Boot microservices to Kubernetes with Jenkins CI/CD and built Kafka-based real-time event streaming (appointment/report events) with idempotent consumers to avoid duplicate processing.”

Prasad Sadineni

Screened

Mid-level AI Engineer specializing in LLM fine-tuning, RAG, and agentic systems

Nashville, TN6y exp

“Building and deploying production in-house, domain-specific LLM chatbots for enterprises that cannot use third-party GPT tools due to internal policies. Focused on reducing latency and improving domain awareness using fine-tuning, continual learning, and advanced RAG/agent retrieval strategies, with experience orchestrating multi-agent workflows via LangChain/LlamaIndex and vector DBs (FAISS, Weaviate, Chroma).”

Krystal Galdamez

Screened

Junior Full-Stack Software Engineer specializing in AI-powered web applications

San Jose, CA1y exp

“Startup-focused engineer who has shipped Python backend features, AI integrations, and Playwright automation for products including an AI coaching platform and hiring workflow tools. Stands out for working through ambiguous zero-spec environments, hardening flaky Firebase-authenticated test flows, and designing practical fallback paths when AI outputs are unreliable.”

“IBM Power/AIX engineer who has owned a large production estate (20+ Power9/Power10 frames and 400+ LPARs) with vHMC and dual-VIOS HA. Has hands-on incident recovery experience (NPIV/RMC issues, LPM restores) and PowerHA failovers, plus modern DevOps exposure using Terraform on AWS and CI/CD with GitHub Actions/Jenkins (including deploying AI/RAG and vision workloads).”

“Backend/AI engineer who built and refactored a production RAG system over IRS Form 990 filings for 60 nonprofits, using a dual-path architecture (deterministic financial ranking + TF-IDF semantic retrieval) to keep latency sub-2s and reduce hallucinations. Demonstrates strong API craftsmanship in FastAPI (contract-first, OpenAPI-driven) plus production-grade security for multi-tenant systems (JWT, RBAC, Supabase-style RLS) and careful migration practices (feature flags, traffic mirroring, incremental rollout).”

Navaneeth Yadamreddy

Screened

Junior Unity Game Developer specializing in Android games and Firebase-backed apps

Bengaluru, India1y exp

“Unity/C# student developer (IST) who built a networking simulation to reduce transmitted movement data and improve perceived smoothness/stability. Has hands-on experience integrating LLM-driven NPC dialogue via API/JSON prompting with token/cost controls, plus AI navigation work using NavMesh baking and snapping; also tested Unity UI/canvas scaling issues on Meta Quest vs Android.”

Wilson Huang

Screened

Junior Backend & Full-Stack Engineer specializing in Python/FastAPI and cloud services

Binghamton, NY4y exp

“Robotics software contributor from Binghamton University’s drone research lab who built a Dockerized, multithreaded Python control stack integrating Crazyflie firmware for low-latency, real-time coordination of multiple drones. Hands-on with telemetry/command pipelines, profiling and control-loop optimization, and wireless comms using CrazyRadio PA.”

“Unity/C# gameplay and rendering engineer who built a custom per-object shadow system in URP that improved performance from roughly 30 FPS to 80+ FPS while preserving high-quality dynamic shadows. Also built a personal multi-process AI/LLM workflow platform with custom prompt/control protocols, streaming UX, and cost-optimized memory/caching architecture—showing unusual depth across both real-time graphics and applied AI tooling.”

“Graphic Designer focused on modern, high-polish marketing creative across static and video. Builds brand-specific Figma design systems (exporting live sites via HTML-to-design plugin, then structuring foundations/components with heavy auto-layout and variants) to support fast bulk edits and high-volume output. Produces short-form AI-driven marketing videos in CapCut with hook-first pacing and modular templates, and iterates quickly with growth teams via async Slack feedback cycles.”

“Python backend developer from Larix Technologies who built and scaled microservice APIs for an omnichannel messaging SaaS (WhatsApp/Instagram/Facebook) and led production performance fixes during peak traffic, cutting webhook latency ~50%. Also shipped applied AI products end-to-end: a RAG-based PDF assistant (LangChain + Mixtral via Groq + React) and a BI agent that plans/executes/verifies multi-step analytics with strong guardrails and auditability.”