Vetted Retrieval-Augmented Generation (RAG) Professionals

“Built and owned a production conversational AI platform for a healthcare contact center, including RAG-based agent assist, hybrid retrieval, safety guardrails, and production monitoring. Stands out for combining LLM product delivery with strong operational rigor, driving a reported 25-30% improvement in handling time in a sensitive healthcare environment.”

“ML engineer with production experience at PayPal and Flipkart, owning high-scale systems across fraud detection, recommendations, and LLM tooling. Stands out for combining strong modeling judgment with practical platform engineering, delivering measurable impact like 22% fewer fraud false positives, 18% CTR lift, 40% less LLM manual review, and 30% faster redeployments.”

“Built and launched a production self-healing MLOps agent that autonomously diagnosed and fixed model training failures on Kubernetes GPU infrastructure. Combines deep AI infrastructure knowledge with full-stack product ownership, and has delivered measurable impact including 35% less infrastructure waste, nearly 50% less troubleshooting time, and 60% lower LLM API costs.”

Kiran Kumar

Screened

Mid-level Software Engineer specializing in Java microservices and GenAI automation

USA4y exp

“Software engineer (4+ years) with hands-on production GenAI experience: built an AI incident triage assistant that summarizes production logs for on-call engineers and iterated it using real incident metrics (time-to-signal, triage duration). Also shipped a RAG-based customer support knowledge assistant using embeddings + vector retrieval with strong guardrails (relevance thresholds/abstain, sanitization, auditing) and a formal eval loop (500-query gold set) that drove measurable retrieval improvements.”

“Director-level Senior Manager of Software Engineering at Discover with roughly a decade in web application engineering leadership, focused on modernizing legacy banking platforms into cloud-native SPA architectures. Stands out for combining large-team people leadership with hands-on technical depth in architecture, debugging, and prototyping, including GenAI experimentation and high-scale customer-facing migrations.”

“Architecture leader from Disney who managed system, AI, and data architects while staying hands-on in solution design. Has experience building LLM-based video advertising products, designing Kafka-based real-time data architectures, and using MVP/POC approaches to align product and executive stakeholders.”

David Richards

Screened

Staff enterprise architect specializing in governance, automation, and regulated environments

Remote, USA18y exp

“Solutions/Sales Engineering professional who has supported enterprise and upper mid-market B2B SaaS deals across highly regulated industries, then transitioned into enterprise architecture and governance at IQVIA. Stands out for combining AI/RPA solution selling with hands-on architecture and implementation, including a legal AI classification deal that achieved 97% accuracy with zero false positives and an air-gapped UiPath deployment that automated 37% of incoming insurance documents.”

“Full-stack engineer with hands-on ownership of a customer-facing advanced performance metrics experience in the Amazon S3 console, spanning React UI, Python/Node services, Redshift/RDS data access, and AWS IaC/CI-CD with CloudWatch/Route53 operational readiness. Demonstrates strong production instincts around resilience (partial failures, multi-region inconsistencies), progressive rollouts/feature flags, and reliable ETL/integration patterns (idempotency, backfills, reconciliation).”

Ranfei Pang

Screened

Mid-level Software Engineer specializing in AI systems and FinTech

Boston, MA4y exp

“Amazon warehouse-tools engineer with strong full-stack and GenAI systems experience, spanning large-scale provisioning platforms and internal LLM/chatbot products. They’ve owned systems end to end, including React/TypeScript frontends, Java/AWS backend orchestration, and Bedrock-based RAG architectures, with measurable impact on latency, token cost, validation quality, and operational support load.”

“LLM/agentic systems builder at Verizon who deployed a LangGraph-orchestrated multi-agent ticket-automation platform with RAG (FAISS) to replace brittle rule-based bots. Improved routing correctness by ~30–40%, hit ~300ms latency targets via model routing, and reduced ops workload by ~60% through tight iteration with non-technical stakeholders and strong testing/observability practices.”

“Enterprise Architecture leader with insurance domain experience (Farmers Insurance) who drove a multi-phase roadmap to modernize a siloed CRM landscape—migrating from legacy Siebel to Salesforce Financial Services Cloud with Customer 360, MDM, and omnichannel capabilities. Also led a high-impact architecture decision to implement offline billing to reduce customer-facing downtime, including complex SAP/on-prem-to-cloud integration and transaction sync.”

“Software engineer with experience at Striim and Amazon who ships end-to-end production systems across UI, backend, ML, and operations. Built a real-time PII detection capability for a streaming data platform by integrating Python ML inference into a Java monolith via gRPC sidecars, achieving ~3M events/hour throughput and ~93% accuracy, and helped drive enterprise adoption (Fiserv, CVS). Also modernized internal Amazon tooling for multi-region scale with modularization and fully automated deployments.”

“Backend/platform engineer with payroll domain depth who built high-volume payroll processing microservices (Java/Spring Boot, Kafka, PostgreSQL, Redis) on AWS Kubernetes and debugged major peak-cycle latency by redesigning transaction boundaries and moving to async Kafka processing (>50% latency reduction). Also shipped an LLM-powered HR assistant using RAG with strong security/guardrails (RBAC, PII masking, audit logs) that cut support tickets by 40%, and designed reliable multi-step agent workflows with retries, circuit breakers, and idempotency.”

“Backend/LLM engineer who built a production-critical Amazon Bedrock + RAG correction and compliance layer for employee communications, integrating tightly with existing Spring Boot/AWS microservices to reduce manual review while keeping outputs explainable and auditable. Also designed an event-driven system processing 10M+ events/day (SQS/Lambda/DynamoDB/Elasticsearch) and handled on-call incidents with strong observability and reliability patterns (idempotency, retries, hotspot mitigation).”

“Infrastructure/DevOps engineer with primary ownership in enterprise Linux and AWS/Azure production environments (including financial systems). Built secure, repeatable CI/CD pipelines deploying containerized workloads to EKS/ECS and implemented Terraform/CloudFormation IaC with drift detection and rollback practices; lacks direct IBM Power/AIX/PowerHA experience.”

“Built and shipped a production enterprise RAG knowledge assistant that returns grounded, cited answers and uses confidence-based fallbacks (clarifying questions/abstention) with monitoring and compliance controls for sensitive data. Implemented end-to-end agent orchestration (function calling, structured JSON, state, retries/rate limits) plus eval/feedback loops, and achieved a reported 30–40% improvement in knowledge-task completion time while reducing hallucinations via retrieval improvements.”

ABHIJOY SARKAR

Screened

Senior AI Engineer specializing in LLMs, agentic systems, and MLOps

San Francisco Bay Area, CA8y exp

“Built and shipped PromptGuard, a production middleware proxy that secures GenAI RAG/agent systems against prompt injection and unsafe tool use using risk scoring, graded policy actions, and least-privilege tool gating. Also replaced LangChain abstractions with a custom state-machine runner for a production voice agent to reduce latency and improve traceability, and delivered a clinic call assistant by converting front-desk/doctor requirements into scenario-based guardrails and measurable evals.”

Deepika Gotla

Screened

Senior Technical Support Engineer specializing in Azure Cloud & Generative AI

Bellevue, WA7y exp

“Microsoft cloud/infra engineer with 5+ years supporting enterprise Azure environments, specializing in security-focused networking (private endpoints, DNS) and production troubleshooting across Azure Front Door/App Gateway WAF/AKS. Has implemented posture improvements via Defender for Cloud, Azure Policy, and RBAC tightening, and also designs secure AWS agent/scanner integrations and modern EKS/GitHub Actions/Secrets Manager observability-enabled SDK rollouts.”

Shriya Bannikop

Screened

Mid-level Software Engineer specializing in cloud platforms, data engineering, and distributed systems

Seattle, WA5y exp

“Full-stack engineer who built and owned an AI-assisted job-matching dashboard in Next.js App Router/TypeScript, keeping LLM logic server-side and improving performance via deduplication, caching/revalidation, and streaming (35% fewer duplicate LLM calls; 40% faster first render). Also has strong data/backend chops: designed Postgres models and optimized queries at million-record scale (1.8s to 120ms) and built durable AWS multi-region telemetry workflows with idempotency, retries, and monitoring.”

Abraham Musa

Screened

Senior Solutions Architect specializing in cloud AI infrastructure and security

Union City, NJ9y exp

“Cloud-native architect focused primarily on AWS, with experience designing Kubernetes and AI/ML infrastructure for customers rather than owning day-to-day operations. Particularly interesting for AI platform roles: they described using Amazon Bedrock to analyze Terraform and automatically generate compliant IaC templates and runbooks for new multi-cloud AI environments.”

“Built and shipped production LLM agents that automate document processing and decision workflows, with a strong focus on reliability, guardrails, and measurable business impact. Stands out for combining RAG, tool calling, evals/monitoring, and ERP integration to deliver 30-35% manual effort reduction and higher throughput without additional headcount.”

“GenAI/LLM engineer who architected and deployed a production RAG “research assistant” for JPMorgan Chase’s regulatory compliance team, focused on safety-critical behavior (mandatory citations, refusal when evidence is missing). Deep hands-on experience with LlamaIndex, Pinecone, Hugging Face embeddings, LangGraph agent workflows, and metric-driven evaluation (golden sets, TruLens), including a reported 28% relevancy lift via cross-encoder re-ranking.”

“Applied ML/LLM engineer currently building AppleCare’s production chat recommender, owning the full lifecycle from transcript cleaning and fine-tuning through distributed deployment, monitoring, and iterative improvement. Their work delivered >10% copy-count improvement, 5% lower modification rate, 60% cost reduction, and $1.1M profitability in 2025, and they also created a reasoning-data generation approach that enabled a reasoning model and a judge model that cut eval time by over 99%.”