Vetted Semantic Search Professionals

Sree Gautham Alluri

Screened

Mid-level Robotics & AI Developer specializing in autonomous navigation and LLM-powered robotic systems

Exton, PA6y exp

“Robotics Support Engineer at HAI Robotics supporting a 385-robot warehouse fleet at a Shein client site. Built a production automation and reporting workflow to diagnose and resolve abnormal shelf locations, cutting incidents from ~250/day to ~25/day while providing actionable root-cause data to client/ops/maintenance. Hands-on ROS 2 (Humble) debugging across Nav2/localization/TF and sensor integration issues including QoS and firmware coordination.”

“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.”

“Healthcare-focused ML/AI engineer who has built production voice agents and clinical question-answering systems end-to-end, from experimentation through deployment, observability, and iteration. Particularly strong in making LLM systems reliable in real workflows via RAG, fine-tuning, guardrails, evaluation pipelines, and shared Python tooling; cites ~20% clinical QA accuracy gains and ~40% faster physician decision turnaround.”

“Application-focused software engineer working on AI-heavy products, with hands-on experience building end-to-end document processing, retrieval, and configurable workflow systems. Particularly strong in combining React/TypeScript UX, FastAPI/Postgres backend design, and LLM workflow reliability improvements through validation, prompt iteration, and reusable abstractions.”

“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.”

“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.”

“Built and deployed a production LLM-powered demand and churn forecasting system for an e-commerce client, combining open-source LLMs (LLaMA/Mistral) and Sentence-BERT embeddings to generate business-friendly explanations of forecast drivers. Strong focus on data quality and model trust (validation, baselines, segmented monitoring) and production reliability via Airflow-orchestrated pipelines with readiness checks, retries, and ongoing drift/A-B testing.”