Vetted Recommender Systems Professionals

“McKinsey practitioner who built and deployed production LLM systems for consultants/clients, including a Power BI-integrated multi-agent chatbot (RAG + text-to-SQL + formatting) with custom Python orchestration, verification loops, and a 100+ case eval set achieving ~95% consistency. Also delivered a taxonomy-mapper agent that standardized inconsistent labeling for C-suite stakeholders, cutting a process from >2 weeks to <30 minutes through demos and business-focused communication.”

“Built and productionized a real-time enterprise RAG pipeline to improve factual accuracy and reduce LLM hallucinations by grounding responses in constantly changing internal knowledge bases (policies, manuals, FAQs). Experienced in orchestrating end-to-end ML workflows (Airflow/Kubernetes), handling messy multi-format data with schema enforcement (Pydantic/Hydra), and maintaining freshness via streaming incremental embeddings plus batch refresh. Also delivers applied ML solutions with non-technical teams (marketing/CRM) for segmentation and personalized engagement.”

“Backend engineer who helped redesign and refactor Forma’s backend during an app rewrite, emphasizing modularity, maintainability, and A/B testing support while delivering feature parity on a quarter-long timeline. Led a careful database migration using parallel databases with schema differences, validating integrity via staging and SQL checks, and has experience debugging subtle computer-vision overflow edge cases.”

“LLM/Conversational AI engineer who built a production multi-turn dialogue system using LoRA fine-tuning on LLaMA, cutting training compute/memory by 90%+ while maintaining low-latency inference via quantization and streaming generation. Experienced in orchestrating end-to-end ML workflows with Prefect/Airflow/Kubeflow (including hyperparameter sweeps and W&B tracking) and improving agent reliability through benchmark-driven testing, shadow-mode rollouts, and stakeholder-informed guardrails.”

“Frontend-leaning full-stack engineer who built an internal real-time operations dashboard from 0→1 using React, TypeScript, Redux Toolkit, Material UI, and Node.js integrations. Stands out for hands-on performance tuning at scale—profiling and fixing excessive re-renders, optimizing live-update UIs, and iterating post-launch with caching, pagination, and observability.”

“Early-stage full-stack engineer who built Dokai's core web spreadsheet product and key AI features with just a two-engineer team. They combine strong product ownership with practical LLM integration experience, including reducing onboarding from a week to five minutes and solving difficult reliability and memory issues in production.”