Vetted Operating Systems Professionals

“Built and deployed a production chatbot on osvaldocalles.com and iterated through real-world LLM engineering issues: model quota/cost tradeoffs (migrating to Nova Pro), RAG accuracy via semantic chunking, AWS IAM/guardrail/security pitfalls, and Lambda/API Gateway streaming constraints (prefers JS for streaming layer). Experienced with agent orchestration using Strands SDK (AWS-focused) and LangGraph (Vercel/container deployments), plus evaluation pipelines using LLM-as-evaluator, dashboards, and staged model rollouts.”

“Entry-level full-stack engineer with internship experience at Amazon (Appstore IAP flow + uninstall recommendation workflow) and a health-tech startup (OneVector) where they built a DSUR reporting workflow end-to-end, including document generation, S3-backed versioning/metadata, and secure preview/download. Demonstrates strong production debugging and reliability mindset (instrumentation, deterministic retrieval, idempotent writes) and focuses on UX/performance in high-stakes user flows.”

“AWS intern who significantly evolved a Drift Audit Service backend (Control Tower/EventBridge context) to make drift findings more explainable and reduce false positives by adding a verification step in Lambda before event ingestion. Demonstrates strong API design fundamentals in Python/FastAPI (contracts, idempotency, security controls) and careful rollout practices (feature flags, canaries, phased deployments).”

“Product/technology leader with deep security and cloud infrastructure expertise who drove a major shift from hardware-based networking/security appliances to cloud-native capabilities, growing cloud revenue from $0 to $400M in 4.5 years. Led an innovative eBPF-based approach (“precryption”) to enable lightweight cloud TLS interception/decryption, and has hands-on coding interest (recent Rust work on a personal cybersecurity identity/trust platform).”

“Robotics software engineer with hands-on ROS2 experience building an audio conversion node and integrating Whisper LiveKit for streaming speech-to-text in a simulated hostile (outer space) robot environment. Also worked on a 2023 LiDAR + ML vision obstacle-detection project for a hospital-nurse-assistant robot, and has strong large-scale CI/CD deployment experience from AWS (2022–2024) across alpha/pre-prod/prod stages.”

“Graphics software engineer with academic robotics/HRI experience at Oregon State University under Dr. Heather Knight, leading a ROS+Python physical robot and Unity/C# VR system to study how motion/texture/collisions are perceived in VR (2 papers + thesis). Also built ROS-based Wizard-of-Oz TurtleBot study systems and multi-robot coordination experiments, plus industry experience with Docker/Kubeflow ML tooling and Azure DevOps CI/CD automation.”

“Interned at SLB and owned an end-to-end GenAI chatbot deployment for a finance team, including invoice PDF data extraction and an LLM-driven layer (LangGraph/LangChain) that translated natural language to SQL and returned results in natural language. Validated LLM JSON outputs against benchmarks using DeepDiff and deployed the solution via Docker to Kubernetes, managing pods with k9s.”

“Software engineer with experience at Amazon and Agora building end-to-end systems: a knowledge-base AI chatbot (React/TypeScript UI + retrieval/response backend + Docker deployment) and an internal approval governance platform using AWS Step Functions and DynamoDB. Emphasizes fast iteration without sacrificing trust via feature-flag rollouts, citation-required answers, abstention on low-confidence retrieval, regression query sets, and strong observability (request IDs, structured logs, latency/error monitoring).”

“Cofounder at MeowyAI who shipped a production multimodal (vision/voice/text) AI task manager using Gemini, tackling real-world issues like hallucinations, tool-calling safety, and RAG-based preference memory. Also built a production multi-agent RAG system orchestrated with LangGraph (and contributes to LangChain), with strong emphasis on latency optimization, observability (OpenTelemetry), and rigorous testing/evaluation including A/B tests and adversarial prompting.”