Vetted AI Engineers

silin liu

Screened

Mid-level AI/ML Engineer specializing in LLM agents, RAG, and enterprise ML systems

New York City, NY5y exp

“Built a production multi-agent recommendation/RAG system for internal data analysts to speed up weekly report creation by improving document discovery and automating report/SQL generation. Implemented LangGraph-based orchestration with deterministic agent routing, robust error handling (interrupt/resume), and metadata-driven semantic chunking for diverse PDF/document formats, plus monitoring for latency, throughput, and token/cost efficiency.”

“Built and deployed a secure, production LLM-based document summarization and risk-highlighting tool for financial auditors, running inside a private Azure environment to protect confidential data. Focused on reliability (hallucination mitigation via retrieval-based prompts and source citations) and validated performance through comparisons to auditor summaries plus a user pilot, cutting review time by about half.”

“Built and shipped a production-grade agentic RAG system at CVS Health for patient adherence and medication recommendations, processing 20k+ patient records/day. Strong focus on real-world reliability: hybrid retrieval tuned with re-ranking (<400ms latency), strict JSON/schema validation and tool guardrails, and monitoring/drift detection that reduced MTTD from 6 days to 18 hours while improving recommendation accuracy (+8%) and cutting escalations (~23%).”

“Built and deployed a RAG-based clinical knowledge assistant at GE Healthcare to help clinicians query large volumes of messy, unstructured clinical documents with grounded, cited answers. Hands-on across the full stack (OCR/ETL, de-identification for PHI, Azure OpenAI embeddings, Cosmos DB indexing, FastAPI/Django) with production monitoring via LangSmith and performance tuning through batching and index optimization.”

“AI engineer with robotics perception experience at Forterra, building and deploying moving-object/obstacle detection models into real-time robot pipelines. Addressed training crashes/latency via sub-batch training and optimizer tuning, and improved debugging using ROS/ROS2 tooling with 3D voxel visualization and color-coded validation.”

Ajay Madhusudhan Thumala

Screened

Junior Software Engineer specializing in data engineering and LLM applications

Irvine, CA1y exp

“Computer science engineer and master’s graduate who independently built a mechatronics-heavy capstone prototype: a smartphone concept for deafblind users using micro-actuator arrays for braille reading. Also has platform engineering experience at Quantiphi, deploying webhooks to Kubernetes and implementing GitOps-based CI/CD using AWS CodeCommit/CodeBuild and ECR.”

Nikhil Soni

Screened

Junior AI/ML Engineer specializing in LLM systems and retrieval-augmented generation

New York, NY2y exp

“Built and deployed a production LLM-powered market intelligence and decision-support platform for noisy, real-time financial data, using a high-throughput embedding + vector DB RAG architecture to reduce hallucinations while keeping latency and cost low. Operated it at scale with GPU-backed inference (continuous batching/quantization), FastAPI on Kubernetes, and Airflow-orchestrated ingestion/embedding/retraining workflows, with strong schema-based reliability and monitoring.”

Wei-Hsien Wang

Screened

Entry-level AI Engineer specializing in full-stack generative AI systems

San Jose, CA1y exp

“AI/full-stack product engineer who has shipped both user-facing and internal LLM products, from a photo-to-music recommendation app to an experimentation agent at Azazie. Stands out for combining modern app development with production-grade agent and GraphRAG systems, including a 500k+ email analysis platform and measurable impact like 3x experiment velocity, 75% setup-time reduction, and 65% faster task discovery.”

“Built an LLM multi-agent “ingredient safety” analyzer for cosmetics that cuts consumer research time from ~20+ minutes to minutes, using LangGraph orchestration, hybrid retrieval (Qdrant + Tavily), and safety-focused critic validation (false rejections reduced ~30%→~8%). Also has research-internship experience building computer-vision pipelines to classify emerald color/clarity by translating gem-expert heuristics into quantitative model features.”

“Siemens AI engineer who shipped production multi-agent LLM systems across cybersecurity and sustainability, including a vulnerability automation agent that cut manual work 70%. Deep in orchestration (LangGraph supervisor-worker state machines), reliability engineering (async fault tolerance, retries, spike handling), and rigorous evaluation (offline benchmarks, LLM-as-a-Judge improving label agreement 28.9%) with measurable production guardrails.”

“Built and owned Alight's AI-powered Search Summary feature end-to-end, using a RAG pipeline with OpenSearch and Bedrock, and drove a 20% increase in user feedback scores. Stands out for bringing rigorous production evaluation to LLM systems via live LLM-as-a-judge monitoring, and for experience with advanced agentic architectures, hybrid search, and reranking at scale.”

“AI/ML engineer who has built a production text-to-image generation system in PyTorch with an AWS-backed inference setup, focusing on GPU-efficient training and embedding-space architectural choices inspired by recent research (e.g., Meta VL-JEPA). Uses both metric-based evaluation (FID) and human testing to validate real-world visual quality, and can translate technical concepts for non-technical stakeholders.”

“UC Berkeley CS–trained hands-on engineering leader with executive experience spanning fundraising and board/customer communication. Led architecture and roadmap for AI-driven fintech platforms (including portfolio data, market signals, document processing, and Bitcoin trading), scaling global orgs (~100 people) and driving modular API-based designs that improved reliability, onboarding speed, and customer retention.”

“LLM/RAG practitioner who productionized an LLM-driven customer communication and transaction understanding system at PayPal, emphasizing privacy/compliance guardrails and large-scale data normalization. Experienced in real-time debugging of hallucinations via retrieval pipeline tuning and in leading hands-on developer workshops and sales-aligned POCs to drive adoption.”

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.”