Vetted Retrieval-Augmented Generation (RAG) Professionals

“Built and productionized an internal LLM-powered document Q&A system at Morgan Stanley using a LangChain-based RAG pipeline (FAISS + OpenAI) with AWS ingestion (S3/Lambda), handling 100k+ pages and cutting lookup time ~35% while keeping responses under 3 seconds. Strong on reliability: automated evals/CI (pytest + GitHub Actions), CloudWatch monitoring, drift detection (prompt drift and fraud-model drift), and security controls (IAM + app-level authorization) in a financial-services environment.”

“Built GoEngineer’s first production AI systems, including an end-to-end RAG pipeline for SolidWorks technical support using Azure Blob Storage, Azure AI Search, and Azure OpenAI, plus an AI summarization feature adopted by sales/customer success. Strong in productionizing LLM workflows with evaluation harnesses (golden sets, LLM-as-judge, red teaming, shadow deploys) and Azure infrastructure integrations (Redis, Service Bus, App Insights), and has also implemented a custom MCP server for agentic monitoring.”

“Built and shipped production LLM/RAG systems at Mayo Clinic, including a conversational AI assistant for patient pre-consultation and a clinical-trial matching tool for doctors. Implemented HIPAA-compliant de-identification and guardrails, plus real-time feedback logging and fine-tuning that improved response accuracy by 15% and reduced admin workload by 25%.”

“Built and shipped a production LLM-powered customer support triage/resolution agent that automated ~60% of tickets, cutting response times from hours to seconds and improving first-response resolution by ~40%. Experienced designing multi-tenant, tenant-isolated agent architectures with RAG, schema-based tool calling/strict JSON validation, and strong reliability practices (guardrails, retries, fallbacks, monitoring), including safe integration with messy ERP-like data.”

Yasser Ali

Screened

Junior AI & ML Engineer specializing in agentic systems and full-stack AI products

San Francisco, CA2y exp

“Won a machine learning contest and was placed onto a Kaiser data science team, where they built ML models for hospital bottleneck prediction and resource allocation. They later built and deployed a full-stack LLM-based “data analyst agent” (with custom orchestration plus LangChain/OpenAI Agents experience) that generates analysis code, answers questions, and produces dashboards from uploaded datasets, emphasizing rigorous evaluation sets, robustness, and healthcare security/compliance integration.”

Dinesh Kumar Patibandla

Screened

Mid-level Machine Learning Engineer specializing in LLMs and RAG for finance and healthcare

Texas, USA4y exp

“ML Engineer with recent Goldman Sachs experience building and deploying a production RAG/LLM assistant for summarization, drafting, and internal knowledge retrieval across financial, risk, and compliance documents. Designed for heavy regulatory constraints and scaled to 10,000+ concurrent users using Kubernetes-based orchestration, dynamic LLM routing, and rigorous testing (adversarial prompts, A/B tests, load simulations) with privacy controls like differential privacy.”

Pavan Kumar Malasani

Screened

Mid-level AI/ML Engineer specializing in financial risk, fraud detection, and GenAI

Remote, USA4y exp

“GenAI/ML engineer in Citigroup’s finance environment who has deployed production RAG systems for investment banking under strict privacy and model-risk constraints. Built an internal-VPC Llama2 + Pinecone + LangChain solution with NER redaction and citation-based verification to prevent hallucinations, delivering major time savings, and also partnered with global finance executives to ship an AI early-warning indicator for treasury/liquidity risk.”

Yukti Kamthan

Screened

Senior Software Engineer specializing in AI/ML and data systems

Mumbai, India10y exp

“Built and shipped production LLM/AI agent systems including an NL-to-SQL query agent with semantic search and Redis-based caching, using schema-aware prompting and threshold validation to reduce hallucinations. Has orchestration experience running ML microservices on Kubernetes and automating event-driven insurance (P&C) workflows (claims/policy + fraud checks), reporting ~60% manual overhead reduction and ~99% uptime, with strong monitoring/drift-detection and business-facing Power BI reporting.”

HEMANTH KUMAR KOTTAPALLI

Screened

Mid-level Machine Learning Engineer specializing in GPU-accelerated LLMs and MLOps

GA, USA4y exp

“Built and deployed a production LLM-powered decision-support system for supply-chain planners that explains demand forecast changes using grounded retrieval from sales, promotion, inventory, and supplier data. Implemented strict anti-hallucination guardrails and latency optimizations, deployed as a real-time AWS API with monitoring, and reported ~15% forecast accuracy improvement and ~12% supply-chain risk reduction. Experienced orchestrating data/ML/LLM workflows with Airflow, LangChain/LangGraph-style patterns, and AWS Step Functions while partnering closely with non-technical business users via demos and example-based requirements.”

Sachin Reddy Kunta

Screened

Mid-Level Backend Software Engineer specializing in payments, fraud systems, and AI agent infrastructure

San Francisco, CA3y exp

“Early-career engineer who owned an end-to-end objective assessment/coding contest platform at an edtech startup, using Postgres + S3 and Redis (queues + ZSET) to decouple and scale code submission processing with worker sandboxes. Also implemented idempotency controls and set up monitoring and CI/CD while the rest of the team focused on curriculum.”

Qice Sun

Screened

Junior GenAI Software Engineer specializing in multimodal RAG and agentic workflows

Sunnyvale, CA2y exp

“AI/LLM engineer with production experience building a multimodal RAG agent for Walmart driver support, combining hybrid retrieval (dense+BM25) and fine-tuned Llama 3 served via vLLM on Azure AKS to reach sub-second latency. Drove measurable impact (25% fewer escalations, 60% lower token costs, 33% lower storage costs) and also built Kafka-based microservices that cut batch runtime from 2 hours to 15 minutes and reduced DB load by 80%.”

Atyab Hakeem

Screened

Junior Data Scientist / ML Engineer specializing in GenAI and computer vision

San Francisco, CA2y exp

“Software engineer who built and deployed OddPulse, a multi-agent LLM-powered continuous financial auditing system aimed at reducing compliance penalties by catching issues before audit cycles. Experienced with TrueAI-based agent orchestration, Airflow on GCP batch workflows, and rigorous evaluation/benchmarking (hit rate/MRR, latency/TTFT, cost) alongside security controls for sensitive financial data.”

Pandari G

Screened

Mid-level Machine Learning Engineer specializing in Generative AI and RAG systems

San Francisco, USA5y exp

“GenAI/LLM engineer with production deployments in both fintech and retail: built an AI-powered mortgage document analysis/automated underwriting pipeline at Fannie Mae (OCR + custom LLM) cutting underwriting review from 3–4 hours to under an hour with privacy-by-design controls. Also helped build Sephora’s GenAI product advisory bot using LangChain-orchestrated RAG (Azure GPT-4, Azure AI Search, MySQL HeatWave vector search), focusing on grounding, evaluation, and compliance-aware architecture choices.”

Ravi Ada

Screened

Executive CTO specializing in digital health platforms, cloud & AI, and FHIR/HL7 interoperability

Carrollton, TX22y exp

“Healthcare diagnostics/health tech founder building Casandra.ai, an API-driven lab test catalog and ordering platform designed to standardize fragmented test catalogs and integrate into provider workflows via FHIR. Bootstrapped and built a deploy-ready product, drawing on prior startup experience and accelerator participation (Health Box, DreamIt Ventures).”

Sarthak Vinayaka

Screened

Mid-Level Full-Stack Software Engineer specializing in enterprise AI, data pipelines, and scalable APIs

Redwood City, CA3y exp

“Forward-deployed engineer/tech lead who built an end-to-end demand planning and forecasting application for a major US steel manufacturer, integrating Snowflake data into the C3 platform with batch/MapReduce workflows, monitoring, and a React/TypeScript UI. Also productionized an enterprise LLM integration with structured outputs and authorization guardrails, reporting +30% stakeholder engagement and broad adoption across customer deployments.”

Yash Rangucha

Screened

Mid-level Software Engineer specializing in backend microservices and real-time streaming

Illinois, USA4y exp

“Built and owned an end-to-end LLM-powered enterprise retrieval pipeline at ServiceNow, spanning ingestion of structured/semi-structured sources through vector retrieval and real-time API serving. Focused heavily on reliability and quality (multi-stage validation, monitoring, evaluation pipelines) while also driving performance improvements (~35% faster responses) via caching, async processing, and SQL/query optimization.”

Cuichan Wu

Screened

Junior Full-Stack Software Engineer specializing in scalable, AI-powered web apps

Bettendorf, IA1y exp

“Frontend-leaning engineer with production React experience and hands-on Next.js App Router patterns (Server/Client Components, Route Handlers, caching/revalidate decisions). Has built internal sales dashboards and optimized both React UI performance and SQL Server-backed analytics queries, and previously created an onboarding framework at Adobe that evolved into a configurable, multi-team reusable platform in a lean environment.”

“ML/AI engineer with hands-on experience building production healthcare AI systems across predictive modeling and GenAI. They built an end-to-end patient risk prediction platform and a RAG-based clinical summarization feature, combining strong NLP/LLM skills with AWS deployment, monitoring, drift detection, and reusable Python service design to deliver measurable clinical and operational impact.”

Vamsi Reddy

Screened

Mid-level AI/ML Engineer specializing in healthcare and financial ML systems

Nashville, TN5y exp

“ML/AI engineer with hands-on experience shipping both predictive healthcare models and clinical GenAI assistants into production. They combine strong MLOps depth across Azure and AWS with healthcare-specific safety thinking, including PHI guardrails, retrieval grounding, and production monitoring, and they also built internal Python tooling for fraud ML workflows at Capital One.”

“Backend/ML engineer who built and operated a production WhatsApp assistant end-to-end using a modern RAG stack, delivering >90% automation with sub-2-second latency. Shows strong depth in retrieval quality, observability, evaluation, and incident handling, and has also applied similar AI workflow patterns to a clinical diagnostic assistant processing medical PDFs.”

“ML/AI engineer with strong production depth across classical ML, MLOps, LLM/RAG, and scalable Python data platforms, with experience at Cisco and Accenture. Stands out for tying technical decisions to measurable business outcomes, including $1.2M annual savings, 40% faster support resolution, and broad internal adoption of shared engineering frameworks.”

“AI/ML engineer with production experience across both classical ML and Generative AI, including a real-time banking fraud detection platform at Deloitte and a RAG-based cybersecurity threat analysis feature at Accenture. Stands out for owning systems end-to-end—from feature pipelines and model tuning through deployment, monitoring, retraining, and API/platform reliability—with measurable impact on fraud accuracy, false positives, and SOC analyst efficiency.”

“Built and shipped a production LLM feature that converts natural-language search requests into Lucene queries for OpenSearch-backed device event data, improving usability for non-technical users. Brings hands-on experience across the full stack of agentic systems: model training, FastAPI/React integration, Kubernetes deployment on AWS, event-driven orchestration with NATS/Kafka, and production-grade evaluation/observability.”

“AI engineer and current tech lead building a RAG-based multi-agent QA platform for financial document analysis at significant scale (40,000-50,000 documents). They combine Python, CrewAI, FastAPI, Hugging Face embeddings, Pinecone, and AWS SageMaker to deliver retrieval, calculation, summarization, forecasting, and visualization workflows, while leading a small cross-functional team.”