Vetted Eclipse 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.”

Kevin Thomas

Screened

Intern Software Engineer specializing in AI, cloud, and backend systems

Torrance, CA1y exp

“Candidate has internship and graduate-project experience building AI agents, including a production log-analysis assistant using a lightweight agentic/RAG-style workflow with local GPT training and validation against historical logs. They also worked on Android/iOS game build and release processes in a Unity-based robot racing game environment, and highlight measurable LLM outcomes including 80% analysis accuracy, 2-5 second latency, and 50% cost reduction.”

“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).”

“Data engineer focused on building reliable, production-grade pipelines and data services end-to-end, including a 50+ GB/day pipeline ingesting from APIs/files into Snowflake with PySpark/SQL transformations. Emphasizes strong data quality controls, monitoring/retries, and performance optimization, and has also shipped a Python data API with caching and backward-compatible versioning.”

Venkata Bayarapuneni

Screened

Junior Full-Stack Developer specializing in JavaScript, Python, and cloud-deployed web apps

Remote, USA1y exp

“Built and deployed a production LLM-powered travel assistant (Globe Trote) that automates end-to-end trip planning using a multi-step agent pipeline with RAG, external API calls, and enforced structured JSON outputs. Focused on reliability (validation, retries, fallback prompts, logging) and reported a ~30–40% reduction in irrelevant/generic responses after adding retrieval grounding.”

“Early-career software engineer who has already owned a real-world web product end-to-end for a 100+ member university ACM organization, including requirements gathering, UI/UX improvements, hosting, CI/CD, and ongoing maintenance. Brings hands-on React and full-stack project experience with a strong bias toward practical execution, mobile-friendly design, and reliable delivery.”