Vetted Prompt Engineering Professionals

“Built and operates a production LLM agent for enterprise IT operations that triages and drafts resolutions for high-volume ServiceNow tickets using LangChain + RAG (Pinecone/pgvector) and AWS Bedrock/OpenAI. Emphasizes reliability with schema-validated stages, offline eval datasets from real tickets, and CloudWatch-driven monitoring/guardrails; system scales to 40K+ tickets/month and cut resolution time ~28%.”

Trevor Peace

Screened ReferencesStrong rec.

Senior Full-Stack Engineer specializing in Healthcare IT

San Francisco, CA27y exp

“Founding/sole engineer who has built multiple healthcare products from scratch, spanning medical billing, cardiology triage, and cardiac device monitoring. Particularly compelling for healthtech and AI roles: they combine full-stack TypeScript/AWS execution with strong product judgment in regulated settings, including shipping voice-enabled RAG workflows and rejecting unsafe AI automation when simpler human-in-the-loop UX was the right answer.”

“AI-focused product engineer working on LLM routing, prompt engineering, and multimodal API integrations at production scale. They describe improving system accuracy, latency, and token usage, fine-tuning an internal model to reduce third-party API dependence, and adding safety guardrails through prompt-injection testing and red-team evaluation.”

Nithin Reddy

Screened

Mid-Level Software Development Engineer specializing in distributed systems and event-driven architectures

Santa Clara, California4y exp

“Built and maintained an internal JavaScript/React real-time event monitoring UI used by multiple Goldman Sachs teams (e.g., Private Wealth Management and Bulk Trading Systems). Focused on scaling performance under hundreds of events/sec—using profiling, memoization, batching, and debouncing—and paired it with strong internal documentation and disciplined incident diagnosis via synthetic load testing and logs/metrics.”

“Full-stack product engineer who owned a live-events digital ticketing platform end-to-end, including blockchain-based ticket validation and high-traffic booking flows. Stands out for combining Angular/React frontend work with Java/Spring Boot backend architecture, plus strong production reliability practices around concurrency control, queues, observability, and UX optimization.”

“Built and deployed an Azure-based, fine-tuned CLIP visual retrieval system at Staples for a ~300k-item product catalog, improving edge-case recall by 12% by engineering a custom delta-similarity/dynamic-margin loss. Also has robotics experience using ROS2 for sensor/compute orchestration, including GPS-time-synchronized sensor triggering for robot swarms and latency-bounded optical-flow benchmarking for edge deployment.”

“Built and deployed an AI Copilot for Healthful Telehealth that helps dietitians generate personalized meal plans using patient data and real-time clinical context. Stands out for owning the full lifecycle—from workflow discovery and ETL/RAG architecture to production incident response and post-launch stabilization—while delivering roughly 30% gains in retrieval accuracy and latency.”

“ML/AI engineer with hands-on experience shipping production computer vision and GenAI systems, including a fabric defect detection platform that combined vision models with agentic LLM workflows to reach 89% human-inspector agreement at 200 ms latency. Also built a RAG-based code QA tool for developers and emphasizes production monitoring, evaluation, caching, and reusable Python service design.”

“AI/ML Engineer (TCS) who built and deployed a production LLM-powered audit transaction validation service to reduce manual review of unstructured transaction records and comments. Implemented a LangChain/Python pipeline for extraction/normalization and discrepancy detection, with strong production reliability practices (decision logging, dashboards, labeled eval sets) and a human-in-the-loop auditor feedback loop to improve precision/recall under strict data-sensitivity and near-real-time constraints.”

Ashwith Poojary

Screened ReferencesStrong rec.

Mid-level Software & AI Engineer specializing in Robotics, LLMs, and Reinforcement Learning

4y exp

“Robotics/AI Master's thesis researcher building an LLM-driven workflow to generate and evaluate robot policies before running them in an environment. Also built a local LLM-based real-time target-tracking robot using a pan-tilt camera with LangChain + Ollama, and has hands-on ROS 2/Gazebo experience including URDF-based simulation and a TurtleBot multi-agent chase project.”

suparshwa patil

Screened ReferencesStrong rec.

Mid-level Software Engineer specializing in AI platforms and full-stack systems

Santa Clara, CA4y exp

“Built and shipped a production AI-powered Q&A/RAG onboarding assistant at One Community Global that unified knowledge across Notion, Google Docs, and Slack, cutting volunteer onboarding time by 45%. Demonstrates strong end-to-end ownership: LangChain agent orchestration integrated into a FastAPI backend, rigorous evaluation (200-query dataset, ~85% accuracy), and production feedback/monitoring with source-attributed answers to build user trust.”

“AI engineer who built a production e-commerce system that analyzes product images alongside sales and demographic data to generate actionable creative recommendations, now used by 20+ clients. Also built orchestrated document/agent pipelines (Airflow, LangGraph) including a compliance drift detector auditing 401 compliance documents, with an emphasis on traceability, logging, and production integration.”

“Internship experience building an end-to-end medical AI pipeline that extracts and normalizes messy medical PDFs, fine-tunes BioBERT to classify tumor-related statements (including negation/ambiguity handling), and integrates image-model outputs (MedSAM/GroundingDINO) for tumor localization and classification. Also worked on an LLM/RAG system to draft IPO prospectuses using retrieved regulatory/financial sources (including SEC EDGAR) with structured prompts to reduce hallucinations.”

“Built and launched an internal AI troubleshooting assistant focused on safe, retrieval-first root cause analysis for enterprise systems, with strong attention to monitoring, fallback behavior, and post-launch iteration. Also owns full-stack product work across React and Java/Spring Boot, including high-volume financial operations workflows, and reports measurable LLM improvements such as ~30-40% latency reduction.”

“Backend engineer currently at Citigroup working on real-time transaction processing systems with Kafka. Stands out for using AI tools pragmatically in a regulated banking environment to improve debugging, testing, and developer productivity while keeping human control over architecture, security, and performance decisions.”

Guillermo Salas

Screened ReferencesStrong rec.

Executive software engineering leader specializing in AI-augmented Healthcare SaaS platforms

Elm Grove, WI15y exp

“VP-level software engineering leader in a private-equity-backed company, overseeing a 50+ person org through aggressive growth and operational efficiency goals. Particularly strong in building the operating system around engineering—product-to-engineering governance, AI-augmented SDLC practices, ADRs, and feature-flag-driven delivery—to reduce ambiguity, dependency on institutional knowledge, and cycle time.”