Vetted Embeddings Professionals

“ML/GenAI practitioner with healthcare domain depth who built and deployed a production cervical-cancer EMR classification system using a hybrid rules + medical BERT approach, optimized for high recall under severe class imbalance and PHI constraints. Experienced running end-to-end production ML/LLM pipelines with Apache Airflow (validation, promotion/rollback, monitoring, retraining) and partnering closely with clinicians to calibrate thresholds and implement human-in-the-loop review.”

“LLM/agent engineer who has shipped production RAG chatbots in sustainability-focused domains, including a packaging recommendation assistant that standardized messy user inputs and used Pinecone-backed retrieval over product/regulatory data. Experienced orchestrating end-to-end ML workflows with Airflow and AWS Step Functions/Lambda, emphasizing reliability (property-based testing, circuit breakers, OpenTelemetry) and measurable performance (latency/cost). Partnered closely with non-technical leadership to ship 3 weeks early, driving adoption by 150+ businesses and ~20% reported waste reduction.”

“LLM engineer who has shipped production AI systems, including an RFP requirements extraction platform (OpenAI o4-mini + Azure AI Search + FastAPI) achieving 90%+ accuracy and ~5x throughput through grounding, structured outputs, parallelization, and caching. Also partnered with legal/compliance stakeholders at Nexteer Automotive to deliver an AI document comparison tool with traceability and confidence indicators, adopted by non-technical users and saving ~2 FTEs of review time.”

“Amazon Fire TV Devices engineer who built and shipped a production LLM-powered lab triage and validation system that grounds recommendations in internal runbooks/known-issue data and pushes evidence-based actions via dashboards and Slack. Emphasizes safety and measurability with structured JSON outputs, replay-based evaluation on historical incidents, and production metrics (e.g., disagreement rate and time-to-first-action), plus cost/latency optimizations like caching, batching, and rule-based fast paths.”

“GenAI/LLM engineer and architect who built and deployed a production generative AI financial forecasting and scenario analysis platform at McKinsey, leveraging Claude (Anthropic), LangChain, Airflow, MLflow, and AWS SageMaker. Demonstrates strong LLMOps/MLOps rigor (monitoring, drift detection, automated retraining) and deep experience implementing global privacy controls (GDPR, differential privacy, audit trails) while partnering closely with finance executives and legal/IT stakeholders.”

“LLM/document AI engineer who owned a production-grade contract extraction pipeline at CORAMA.AI, ingesting PDFs and dynamic JavaScript sites from 1,000+ government sources. Built a hybrid deterministic+LLM system with two-phase prompting, Pydantic guardrails, confidence scoring, and human-in-the-loop review—cutting error rates from ~35% to <5% and processing 50k+ documents at ~95% accuracy. Also built clinician-in-the-loop orchestration in research, reducing manual labeling time from 3–4 hours to ~50 minutes.”

“ML/NLP engineer focused on production GenAI and data linking systems: built a large-scale RAG pipeline over millions of support docs using LangChain/Pinecone and added a LangGraph-based validation layer to cut hallucinations ~40%. Also built scalable PySpark entity resolution (95%+ accuracy) and fine-tuned Sentence-BERT embeddings with contrastive learning for ~30% relevance lift, with strong CI/CD and observability practices (OpenTelemetry, Prometheus/Grafana).”

“Summer intern on AWS Lambda tooling team who shipped Finch support in AWS SAM CLI, adding OS/runtime detection and robust fallback behavior to preserve Docker compatibility across developer environments. Also built an end-to-end RAG system for querying arXiv quantitative finance papers using Postgres/pgvector with two-stage retrieval, citation-grounded prompting, and rigorous evaluation loops driven by IR metrics and user feedback.”

“Built the backend for “codeGuard,” an AI-powered static code analysis platform, using FastAPI and Docker. Structured the system into API/service/execution layers and addressed heavy-workload container resource/cleanup issues via strict CPU/memory limits and a queued execution model.”

“Built a production LLM-powered analyst assistant at Discern Security to speed up SOC investigations using a RAG pipeline over security vendor documentation (Python PDF ingestion, vector search). Demonstrates deep, security-critical LLM engineering: structure-aware chunking with custom table parsing, grounded/cited responses, prompt-injection defenses, and post-generation validation, validated via golden datasets and adversarial testing; tool is used daily by analysts.”

“Built an "AskMyVideo" system that turns YouTube videos into queryable knowledge graphs by transcribing audio (Whisper), chunking and embedding content, and enabling traceable answers back to exact timestamps. Strong in entity resolution (rules + fuzzy matching + TF-IDF/cosine with PR-curve thresholding) and modern retrieval stacks (FAISS, hybrid dense/sparse, domain fine-tuning with ~12% precision gain), with a production mindset using Airflow/Prefect, Docker/FastAPI, and LangSmith/Prometheus/Grafana observability.”

“Built and productionized an LLM-powered clinical assistant at a healthcare startup, re-architecting a prototype into a robust RAG system on AWS with guardrails, citations, monitoring, and automated tests for clinical reliability. Works closely with clinicians to convert workflow feedback into evaluation criteria and iterative system improvements, and has hands-on experience debugging agentic systems in real time (including during live client demos).”

“CMU candidate with hands-on experience taking LLM concepts from research prototypes toward production-ready designs (structured outputs, guardrails, failure-scenario evaluation). Also partnered with sales/customer teams at Mazecare to drive adoption with Dontia Alliance (largest dental clinic chain in Singapore) and engaged Singapore government stakeholders, bridging clinical workflow needs with IT security/integration concerns.”

“Built and shipped a production LLM-powered multi-agent RAG system to automate complex internal support workflows, integrating tool execution (SQL/APIs) with validation guardrails to reduce hallucinations. Optimized for real-world latency and cost via model routing, caching, and async parallel tool calls, and enforced reliability with CI-gated golden test sets derived from anonymized production queries.”

“JavaScript/React-focused engineer with meaningful open-source impact: redesigned cache key normalization for a client-side data fetching/caching library using deterministic hashing, added robust test coverage, and collaborated closely with maintainers through GitHub PRs/issues. Also drives measurable runtime improvements by profiling hot paths, refactoring core abstractions, and validating with benchmarks/load tests; has taken ownership of unowned initiatives like improving relevance/ranking in an internal search platform.”

“Built a production LLM-powered RAG agent for healthcare/insurance operations that retrieves and summarizes patient medical documents with grounded citations, scaling to ~4.5M records. Addressed medical shorthand and terminology by fine-tuning ~120 lightweight DistilBERT models by specialty and validating entities against SNOMED/RxNorm, while using SHAP/LIME and human-in-the-loop review to make decisions explainable to stakeholders.”

“QA/validation-focused engineer with experience at Meta testing an ML+LLM content classification/summarization system, including production-vs-test behavior gaps. Built automated E2E validation and drift monitoring (PSI, KL divergence, embedding cosine similarity) run daily/multiple times per day and gated via CI. Also implemented Jenkins-orchestrated Selenium/API test suites in Docker at Capgemini and partnered with a business analyst to convert business rules into automated AI-driven validation checks.”

“ML/NLP practitioner working across healthcare and business/finance use cases: currently fine-tuning a domain-specific Llama 3.1 model for safe reasoning over EHRs/clinical notes using RAG + RL/DPO and RAGAS-based evaluation. Has built UMLS-driven entity normalization pipelines with quantified quality gains and developed embedding/vector-DB systems (FAISS) for semantic matching and forecasting/recommendation applications at Aurora AI and Banxico.”

“Full-stack AI/LLM engineer who has deployed a production LLM backend (Mistral 14B) on GKE to auto-transform datasets and generate runnable ML training pipelines, addressing hallucinations, schema mismatch, latency, and burst scaling with caching/prompt compression and HPA. Also has internship experience (Splunk, BlackOffer) delivering data automation and 10+ Power BI dashboards for non-technical stakeholders with measurable efficiency gains.”

“Built and owned an end-to-end AI-driven decisioning platform at Uber, combining LLM orchestration with typed tool contracts and a Snowflake-based RAG pipeline to make decisions fully auditable. Delivered large-scale measurable impact (120k requests/day, 18k cases auto-resolved/month) while improving ops SLA from 3 days to 6 hours and cutting incident response time nearly in half. Previously led a high-risk strangler-fig modernization of a legacy insurance platform across 120+ microsites at Accenture, coordinating across multiple squads with feature-flagged parallel cutovers.”