Vetted Retrieval-Augmented Generation (RAG) Professionals

“Built and productionized a real-time enterprise RAG pipeline to improve factual accuracy and reduce LLM hallucinations by grounding responses in constantly changing internal knowledge bases (policies, manuals, FAQs). Experienced in orchestrating end-to-end ML workflows (Airflow/Kubernetes), handling messy multi-format data with schema enforcement (Pydantic/Hydra), and maintaining freshness via streaming incremental embeddings plus batch refresh. Also delivers applied ML solutions with non-technical teams (marketing/CRM) for segmentation and personalized engagement.”

“Built and shipped an end-to-end LLM agent during an AT&T internship to automate network troubleshooting, with production-style reliability safeguards (timeouts/retries/fallbacks) and structured, state-machine orchestration; project won 3rd place in AT&T’s nationwide intern innovation challenge and was demoed to leadership. Also handled messy multi-partner data at Tencent by implementing schema validation/normalization, confidence-threshold fallbacks, and idempotent Python/ORM-based pipelines.”

“Built and shipped an LLM-powered data quality assistant that generates maintainable validation checks from metadata while executing validations via Great Expectations, exposed through FastAPI and integrated into Airflow-managed pipelines. Emphasizes production reliability (structured outputs, guardrails, monitoring, versioning, human review) and works closely with compliance/operations teams to deliver clear, auditable, user-friendly AI outputs.”

Jingfei Xu

Screened

Intern/Junior Software Engineer specializing in AI/ML and cloud-based systems

Mountain View, CA0y exp

“Embedded/robotics software engineer with Hyundai Motors experience who owned an AI-driven perception validation pipeline using a Transformer-based approach to generate stable synthetic in-cabin audio for autonomy/ASR testing, cutting downstream testing time by 50%+. Has hands-on ROS integration (IMU sensor streaming, inference, control nodes), MQTT-based distributed messaging, and cloud/container deployment experience (Docker, Node/Express, AWS, CI/CD).”

“Four-time founder with hands-on experience inside angel- and venture-backed executive teams, plus accelerator mentorship experience. Brings a practical, customer-validation-driven approach to company building, with strong insight into early-stage team dynamics and investor ecosystems.”

“Engineering leader with hands-on product and platform experience spanning AI-powered web forms, multi-region Azure/OpenAI architecture, and full-stack team scaling. They also remain close to production systems, citing a concrete debugging example involving iOS WebView local storage behavior causing token loss in embedded mobile web forms.”

john emerson

Screened

Executive product and AI leader specializing in healthcare, public health, and EdTech

Boulder/Denver, CO15y exp

“Veteran healthtech product leader with a track record spanning consumer health, provider workflows, AI voice agents, and public-sector pilots. They have led both large-scale rebuilds and 0-to-1 products, including work tied to Healthline's $21M Series B, a major Healthgrades revenue platform overhaul, and AI healthcare operations products—while consistently emphasizing human-centered design and measurable outcomes.”

“Engineer with startup experience spanning fintech and B2B SaaS, from Playd during rapid growth to Clarity’s AI-powered contract review platform. Particularly strong in React/TypeScript product development for complex, data-heavy workflows used by accountants and finance teams, with supporting experience in Node, Postgres, AWS, and production database design.”

“Internship at BlueFoxLabs building and deploying an AI/ML RAG system for a biopharma client on top of LibreChat, including an AWS Textract ingestion pipeline and PGVector retrieval deployed to AWS EKS. Demonstrated production-minded scalability work by moving from a vertically scaled EC2 setup to a horizontally scaling Kubernetes/EKS deployment, using CI/CD to safely incorporate requirement changes like tabular document data.”

Suparna Roy

Screened

Executive Cloud Infrastructure & SRE Leader specializing in AI-driven reliability and security

Austin, TX14y exp

“Engineering/technology leader with IBM Cloud experience leading large-scale infrastructure modernization from classic architecture to a standardized VPC/next-generation DC platform. Reports major outcomes including cutting region launch time from ~18 months to ~3 months and reducing operating costs by ~80% via automation, modular undercloud services, and platform standardization, while scaling a globally distributed org with clear service ownership and accountability.”

Anand Vallamsetla

Screened

Executive Engineering Leader & Systems Architect specializing in AI, cloud platforms, and FinTech

Los Altos, CA26y exp

“Operator with 20+ years experience and a business degree who led the build and deployment of a Medicaid fraud investigation product for Texas HHSC OIG, cutting investigation time from ~2 years to 90 days. Has government go-to-market experience and has raised a friends-and-family round for an earlier startup concept; now pivoting toward a healthcare-focused venture after a cofounder with core tech could not continue.”

George Liu

Screened

Intern Software Engineer specializing in full-stack, backend, and AI agent systems

Fremont, CA1y exp

“Backend engineer with Tesla experience who redesigned vehicle registration into a step-based, region-configured workflow across 4–5 microservices, enabling partial saves and reducing customer drop-off. Has hands-on experience scaling and securing Python/FastAPI APIs (OAuth2/JWT, CORS), migrating cold data from MySQL to MongoDB via Kubernetes CronJobs, and implementing RBAC/RLS with Supabase + Postgres.”

“Backend/data engineer with Amazon supply-chain experience building production serverless Python services and ETL pipelines on AWS (Lambda, API Gateway, S3, RDS, Glue). Has modernized legacy SAS jobs into Python with rigorous parity testing and phased migrations, and has delivered major SQL performance gains (minutes down to seconds) through indexing and partitioning.”

“Built and shipped a production LLM-powered medical scribe that generates structured clinical visit summaries using RAG, strict JSON schemas, and post-generation validation to reduce hallucinations. Experienced in making LLM workflows deterministic and observable (structured logging/metrics/tracing) and in evaluation-driven iteration with metrics like schema pass rate and edit rate; collaborated closely with clinicians and policy stakeholders at Scale AI to drive adoption.”

“Built and shipped a real-time AI phone agent for small businesses that handles bookings/FAQs/messages using streaming ASR, an LLM with tool-calling, and TTS; deployed to production for multiple paying customers. Demonstrates strong applied LLM reliability practices (tool-first grounding, retrieval, hard-negative testing, and production monitoring) and experience orchestrating multi-step AI workflows with Airflow, Prefect, and AWS Step Functions.”

“Serial entrepreneur who has created several companies, brought them to market, raised as much as $15M, and achieved exits before moving on to new ideas. Combines an academic and institutional background spanning Harvard, MIT, Mass General Brigham, and the Department of War with two decades of consulting experience, and is especially motivated by building impactful technology.”

“Fintech and AI product engineer who has owned major production rollouts, including Lending Club's banking-arm launch, and has since built LLM-powered decision systems for finance and climate use cases. Particularly strong in combining stakeholder management with pragmatic architecture choices like observability, deterministic pipeline design, RAG, and document-to-structured-data workflows.”

“Front-end/product engineer with strong financial-domain experience, including browser-based interfaces for retail planning, sales forecasting, and high-throughput trading data. Stands out for combining UI engineering with machine learning, time-series prediction, browser performance optimization, and functional programming across tools like React, TypeScript, Elm, OCaml, and Scala.”

“Backend/AI engineer who built a production GPU-backed real-time inference API at Nvidia and debugged burst-induced tail latency, cutting P95 by ~29% through dynamic batching and backpressure. Also shipped an end-to-end RAG + agentic operational diagnostics assistant with strict tool controls, evidence citation, confidence gating, and strong production guardrails, plus demonstrated hands-on Postgres optimization (900ms to 40–60ms).”