Vetted Retrieval-Augmented Generation Professionals

Sridhar Duggireddy

Screened

Executive Technology Leader specializing in Cloud Platforms, DevOps, and AI/ML

Tampa, FL21y exp

“Early-stage startup CTO helping build an AI-powered parenting assistant app with features spanning advice, shopping, task management, and inventory management. The team is currently testing an MVP with their network while the candidate simultaneously learns the seed/Series fundraising process through Connectd and early investor conversations.”

“LLM/agent engineer who has built production multi-agent systems (LangChain/LangGraph) for enterprise workflows like email and calendar automation, with a strong focus on latency, tool-calling accuracy, and evaluation via LangSmith. Also worked on AI long-term memory using knowledge graphs at VEAI and communicated the approach and tradeoffs to CEO/CTO stakeholders.”

sai anuragh Sangoju

Screened

Mid-level AI/ML Engineer specializing in fraud detection, credit risk, and NLP

Dallas, Texas4y exp

“Built and deployed a production LLM-powered university support chatbot on Azure using a RAG pipeline, focusing on reducing hallucinations, improving latency, and handling ambiguous queries via confidence checks and clarification prompts. Also has hands-on orchestration experience (Airflow/Azure Data Factory), including hardening a demand-forecasting ingestion workflow with sensors, retries, and automated alerts, and uses a metrics-driven testing/monitoring approach for reliable AI agents.”

“Built a production RAG chatbot for Worcester Polytechnic Institute that indexes 500+ webpages using FAISS + Llama 3, with strong grounding/hallucination controls (confidence thresholds and citations). Also has internship experience orchestrating multi-step ETL pipelines with AWS Step Functions and delivered a 30x faster fraud/claims triage workflow at Munich Re using association rules and stakeholder-friendly dashboards.”

“Built and deployed a production LLM-powered RAG knowledge system to unify operational/policy information across PDFs, wikis, and databases, emphasizing auditability and low-latency/cost performance. Improved answer relevance at scale by moving from pure vector search to hybrid retrieval with metadata filtering and reranking, and partnered closely with healthcare operations/compliance to define acceptance criteria and human-in-the-loop guardrails.”

“Full-stack engineer with payments/settlement domain experience who modernized a payment tracking workflow from REST to GraphQL and delivered a production payment status dashboard using Next.js App Router + TypeScript. Strong in performance and reliability work (Postgres indexing/Explain Analyze, Redis caching, Datadog observability) and in durable event-driven processing with Kafka (DLQs, idempotency, reconciliation, event replay).”

“AI/ML engineer who led Impacter AI’s production deployment of a specialized outreach LLM (CharmedLLM) fine-tuned on GPT-4.1, cutting API costs ~40% while boosting outreach effectiveness ~60%. Built the supporting MLOps and data infrastructure (MLflow, Kubernetes, PySpark, Kafka) and has agentic AI experience from University of Dayton, using LangChain + RAG and vector search (Pinecone) to improve reliability and reduce hallucinations.”

“GenAI/LLM engineer with production experience at Allstate building an end-to-end document intelligence workflow for insurance operations—automating document intake, classification, and risk signal extraction. Emphasizes high-reliability design for regulated/high-stakes outputs using schema enforcement, confidence thresholds, validation rules, and human-in-the-loop routing, with metric-driven offline evaluation and production monitoring.”

Xinyu Li

Screened

Junior Software Engineer specializing in backend systems and AI/LLM RAG platforms

San Jose, CA2y exp

“Full-stack engineer who built and operated a data-driven analytics platform using Next.js App Router/Server Components and TypeScript, owning post-launch monitoring and performance/stability work. Demonstrated measurable wins in analytics performance (e.g., cutting query latency from ~1s to ~200ms) through indexing, query-plan analysis, and precomputation/caching, and has experience designing durable multi-step backend workflows with retries, idempotency, DLQ, and time-correct ordering.”

Chandini Sattineni

Screened

Mid-level Software Engineer specializing in full-stack web, Go microservices, and AI integrations

Remote, USA5y exp

“Backend/LLM engineer who ships production internal tooling end-to-end: automated data-request processing with monitoring-driven improvements (better error diagnostics and lower latency via query/index tuning). Also built a RAG-based internal Q&A system over company docs and operational logs with guardrails (similarity thresholds, fallbacks, response limits) and an eval loop using real user queries and human review to drive prompt/retrieval changes.”

“Repeat founder/CTO with hands-on experience raising capital from friends and family, angels, corporate sources, federal grants, private equity, and venture capital. Built a startup in a software business incubator, later sold the company, and went on to serve as an Engineering Manager at the acquirer inside the Plug and Play accelerator ecosystem.”

“ML/NLP engineer focused on large-scale data linking for e-commerce-style catalogs and customer records, combining transformer embeddings (BERT/Sentence-BERT), NER, and FAISS-based vector search. Has delivered measurable lifts (e.g., +30% matching accuracy, Precision@10 62%→84%) and built production-grade, scalable pipelines in Airflow/PySpark with strong data quality and schema-drift handling.”

“AI/LLM practitioner who has deployed production chatbots across e-commerce, HRMS, and real estate, focusing on retrieval-first workflows for factual tasks like product and property search. Optimized intent understanding and significantly improved latency by using lightweight embeddings and tuning the inference pipeline on Groq (Llama 3.3), while applying modular orchestration and measurable production evaluation.”

“Full-stack engineer who built a live-streaming edtech platform at KratosIQ, owning the entire frontend and the backend streaming layer. Notably migrated the system from a P2P mesh to an SFU architecture to handle scaling under heavy load, and delivered measurable React performance gains (450ms to 40ms render time) validated via Lighthouse and web vitals.”