Vetted Apache Kafka Professionals

“Built a production LLM/RAG assistant for insurance/health claims agents that ingests 100–200 page patient PDFs via OCR (migrated from local Tesseract to Azure Document Intelligence) and delivers grounded claim detail retrieval plus summaries with PII/PHI guardrails. Experienced orchestrating large workflows with Celery worker pipelines and AWS Step Functions (S3-triggered, Fargate-based batch inference/accuracy aggregation), and collaborates closely with non-technical SMEs (claims agents/nurses) through shadowing, iterative demos, and SME-defined evaluation.”

“AI engineer at Anote.ai who built and shipped a production multi-agent LangGraph/LangChain/Ray RAG platform for enterprise search and workflow automation, supporting 3 commercial products and 100+ developers. Drove measurable gains (30% accuracy improvement, lower latency) and improved reliability with Redis-based state checkpointing, message-queue synchronization, and Milvus retrieval optimizations, while partnering with PMs/clients to add transparency features like confidence scores and real-time logs.”

“LLM infrastructure engineer who built a production-critical real-time personalization and memory retrieval system for a user-facing product, adding <100ms P99 latency while improving relevance ~20–25% and holding SLA through 3x traffic. Experienced designing tiered retrieval backends (Redis + vector store), deploying on Kubernetes with autoscaling/circuit breakers, and running rigorous observability, incident response, and agent evaluation (shadow traffic, A/B tests, regression/replay).”

“Capital One engineer leading the architecture and delivery of a large-scale AWS Glue/Spark/Delta Lake batch messaging pipeline that decoupled batch from real-time flows, added multi-region failover and automated retries, and delivered ~40% AWS cost savings with ~3x performance gains. Currently building an LLM-powered Slack bot using RAG to automate message investigations by querying CloudWatch, Snowflake, and internal documentation with privacy-aware masking of NPI/PII.”

“Data engineer at Plaid who built greenfield, end-to-end real-time transaction pipelines and FastAPI data services for fraud detection and analytics, handling millions of events per day. Strong focus on reliability and data integrity via Great Expectations validation, Airflow-based monitoring/SLAs, quarantine/staging patterns, and robust external data ingestion with schema versioning and backfills (reported 50% fewer anomalies and ~40% fewer failures).”

“Backend/data engineer with production experience building credit/fraud enrichment services and checkout pipelines on AWS (EKS + Lambda) using FastAPI, Kafka, Postgres, and Redis, with a strong focus on reliability patterns (timeouts/retries/circuit breakers) and observability. Has also built AWS Glue/PySpark ETL into S3/Redshift with schema evolution and data quality controls, and modernized legacy credit decisioning into Java/Node microservices with parallel-run parity validation and feature-flag rollouts.”

“Built and deployed a production AI/ML SRE copilot that uses RAG over real-time Splunk signals plus deployment/runbook data to generate grounded incident summaries and next steps, cutting time-to-contact by 30%. Treats the knowledge corpus like a production dataset (quality gates, semantic chunking, metadata enrichment) and runs golden-dataset automated evals to ensure reliability, while partnering closely with ops/support leaders through discovery sessions and metric-driven demos.”

“Engineering leader at Bayer Crop Science leading a Core Platform team responsible for widely used open-source TypeScript/React and mobile SDKs (npm/GitHub) embedded across 10M+ monthly active devices. Known for shipping high-performance, backward-compatible developer frameworks with rigorous release discipline (bi-weekly releases, 99.99% uptime, long streaks of zero breaking changes) and major DX wins (onboarding cut to minutes, support tickets down 82%).”

“Engineering leader who managed a 20-person cross-functional team building customer-driven software solutions, delivering a 50% reduction in simulation/test lifecycle and securing a long-term strategic SLA. Strong in scalable data ingestion architectures (FastAPI + Kafka + multiprocess workers), operational diagnostics (correlation IDs/centralized logging), and microservice decoupling for analytics/visualization. Active open-source contributor who shipped a NATS bug fix and improved SDK onboarding with automation that cut ramp time by 30%.”

“Technology leader with experience owning enterprise roadmaps and executing large-scale platform standardization during rapid M&A—most notably driving a tech roadmap across a 37-company portfolio at Regent, tackling technical debt and security gaps via unified cloud-native architecture, IAM/logging, CI/CD, and a global SRE model. Previously scaled an Adobe engineering org from 8 to 40+ across four regions, implementing clear org design, KPIs, and an extreme-ownership culture to support 24/7 operations and enterprise needs.”

“Backend-focused engineer with hands-on experience modernizing a legacy SNMP/PNM data collection system at CableLabs into a cloud-accessible Kubernetes pipeline, feeding Prometheus-formatted metrics into VictoriaMetrics and visualizing real-time network health in Grafana for 100+ modems. Also built a FastAPI + Supabase appointment booking portal for a clinic with encryption and phone-number-based auth, and has frontend experience debugging S3-based HEIF image rendering issues.”

“Built and shipped production improvements to a Paylocity RAG-based AI assistant, redesigning retrieval into a hybrid HNSW + keyword pipeline and using tuned RRF to fuse rankings—cutting latency by ~2s and reducing token usage by ~5000. Previously spearheaded Apache Airflow integration across ETL pipelines at Acuity Knowledge Partners, creating reusable templates and automated triggers to reduce manual job monitoring.”

“Entrepreneurially minded operator with experience in trading-platform environments who prototyped a vector-database layer to generate contextual incident narratives and reduce MTTR/escalations. Also building a non-tech venture: luxury wine distribution into India and broader Asian markets, sourcing directly from wineries with a Master of Wine and planning tier-1 launch via restaurant-owner connections while navigating complex import duties and licensing.”