Vetted Latency Optimization Professionals

“Capgemini engineer with 4+ years building and deploying high-availability, low-latency fraud detection APIs and multi-cluster distributed systems for a Fortune 20 bank, including zero-downtime production rollouts and multi-layer (SQL/network/hardware) performance debugging. Also built a Python + OpenAI/LangChain LLM-powered grading workflow for Austin School for Women, cutting feedback time from 90 minutes to 5 minutes per submission for 200+ learners.”

“Robotics software engineer with deep ROS2 Humble/Nav2 experience who built an SDF-based navigation system (RRT* global planning + gradient-based local avoidance) and implemented scan-matching localization. Proven real-time performance debugging and optimization on hardware (Unitree B1), including halving compute-cycle latency and resolving ROS2 jitter/message-drop issues through explicit QoS and executor/callback-group design.”

“Engineering leader (Director/VP level) who has repeatedly aligned product and engineering through ROI-driven quarterly roadmaps and strong stakeholder communication, including board presentations. Built a parallel cloud team to migrate an on-prem product to the cloud, credited with delivering $9M ARR, and led a Python monolith-to-serverless event-driven microservices transformation. Currently manages distributed teams across Mexico, India, and the US using pod-based structures, clear KPIs, and a supportive accountability culture.”

“Built and shipped a production AI-powered Q&A/RAG onboarding assistant at One Community Global that unified knowledge across Notion, Google Docs, and Slack, cutting volunteer onboarding time by 45%. Demonstrates strong end-to-end ownership: LangChain agent orchestration integrated into a FastAPI backend, rigorous evaluation (200-query dataset, ~85% accuracy), and production feedback/monitoring with source-attributed answers to build user trust.”

“Interned at Larsen & Toubro where they built and deployed an agentic RAG document question-answering system to reduce time spent searching documents and improve trustworthiness. Implemented ReAct-style multi-step orchestration with LangChain/LlamaIndex plus evidence-bounded generation, grounding/citations, and rigorous evaluation—cutting latency ~40%, hallucinations ~35%, and unsafe outputs ~40% while collaborating closely with non-technical business/ops stakeholders.”

“AI/ML infrastructure-focused engineer who has built production RAG systems from scratch (Supabase/pgvector + OpenAI embeddings) and iterated using formal eval metrics to improve retrieval quality. Also debugged real-time audio issues in a LiveKit-based pipeline by correlating packet loss with VAD behavior, and has deep experience building brittle, customer-specific financial platform integrations in Python/Playwright (2FA, redirects, token refresh, rate limits).”

“Built and deployed a production LLM-powered document Q&A system enabling natural-language querying of large PDFs, focusing on retrieval quality (overlapped chunking) and low-latency performance (optimized embeddings + vector search). Experienced with scaling ML/LLM workflows using async/batch processing, caching, cloud storage, and orchestration via Apache Airflow with robust testing, monitoring, and failure handling.”

“Verizon engineer who productionized an LLM-based personalization capability for a customer-facing digital platform, owning the path from success metrics through scalable APIs, A/B validation, and post-launch monitoring (latency/accuracy/drift). Experienced in diagnosing and fixing real-time LLM/RAG workflow issues under peak load, and in enabling adoption via tailored technical demos/workshops and sales support materials.”

“Built and deployed a production LLM-powered lesson adaptation platform for K–12 educators that personalizes content for multilingual and neurodiverse students using RAG and content transformation. Owned the full stack from FastAPI backend and OpenAI integration through reliability/safety controls, latency/cost optimization, and weekly shippable modular APIs, iterating directly with curriculum stakeholders to reduce hallucinations and improve educator trust.”

“LLM/RAG engineer with production deployments in highly regulated domains (Frost Bank and GE Healthcare). Built secure, explainable document-grounded Q&A systems using LoRA fine-tuning, strict RAG with confidence thresholds, and citation-based responses; also established evaluation/monitoring (golden QA sets, hallucination tracking, drift) and achieved ~40% latency reduction through retrieval/prompt tuning.”

“Built and iterated an end-to-end virtual waiting room for a real-time ticketing prototype, making concrete architecture tradeoffs (polling + Redis Pub/Sub) and improving performance post-launch with Redis caching (+30% throughput, -15% p99 latency). Also has hands-on experience building Spark/HDFS ETL pipelines with strong reliability/observability patterns and running disciplined NLP model evaluation loops on review-rating classification.”

“Built and deployed a GPT-based RAG enterprise search system for healthcare clinicians, emphasizing low-latency performance and reduced hallucinations while maintaining end-to-end HIPAA compliance. Demonstrates deep applied experience with PHI-safe data governance (detection/redaction/de-identification), secure Azure ML deployment patterns, and orchestration of production LLM workflows using LangChain and Airflow.”

“Built and deployed a production compliance automation RAG system (at Citi) that generates citation-backed, schema-validated risk summaries for regulatory document review. Emphasizes regulated-environment reliability with retrieval-only grounding, abstention, confidence thresholds, and immutable audit logging, plus orchestration using LangChain/LangGraph and Airflow. Reported ~60% reduction in compliance review effort while maintaining high precision and traceability.”

“Built and shipped a production LLM-powered internal operations automation platform using LangChain RAG (Pinecone) and FastAPI microservices, deployed on AWS EKS, serving 10k+ daily interactions. Implemented a rigorous evaluation/observability stack (golden datasets, prompt regression tests, MLflow, retrieval metrics, hallucination monitoring) that drove hallucinations below 2% and improved reliability, and partnered closely with non-technical ops leaders to cut manual lookup work by 60%+.”

“Built a production internal LLM-powered knowledge assistant using a RAG architecture (Python, LLM APIs, cloud services) that answers employee questions with sourced, grounded responses from internal documents. Demonstrates strong practical depth in retrieval tuning (chunking/metadata filters), orchestration with LangChain, and production reliability practices (latency optimization, automated embedding refresh, evaluation metrics, logging/monitoring) while partnering closely with non-technical operations teams.”

“AI/LLM engineer who built a production autonomous GenAI content ecosystem that generates short-form scripts, extracts viral highlights from long-form video, and dubs content into 33+ languages. Focused on making LLM outputs production-safe via schema enforcement, token-to-time alignment, critic-agent verification, and scalable async orchestration—cutting manual workflows by ~90% and saving $200k+ annually.”

“Built and shipped a production multi-agent conversational AI platform (Monitor agent + RAG + 4 additional agents) with enterprise REST APIs, using ChromaDB-grounded WCAG knowledge to keep responses accurate while varying tone via personality modes and conversation memory. Has experience at LinkedIn delivering technical demos and pre-sales guidance to both engineering teams and C-level stakeholders, acting as a translator between sales and technical teams to drive adoption.”

“LLM/agentic systems builder who has deployed multi-agent educational chatbots using LangChain + LangGraph, with LangFuse-based tracing and FastAPI hosting. Focused on production reliability and performance (latency reduction via agent decomposition and caching) and on evaluation/testing (routing test scenarios, LLM-as-judge). Partnered with product to add image understanding by parsing and storing images in S3, expanding chatbot coverage to 30+ books with images.”

“Backend/distributed-systems engineer (Amazon; also Bank of America) pivoting into robotics software. Built and owned an end-to-end cross-region event processing service for Aurora Global Databases, emphasizing correctness under latency/clock skew, fault tolerance, and strong observability; brings deep Docker/Kubernetes and CI/CD experience to robotics infrastructure and reliability work while ramping up on ROS 2.”

“Built and shipped LLM/RAG systems in finance and startup settings, including a Goldman Sachs document intelligence platform that indexed ~8TB of regulatory filings and delivered cited, conversational answers with <2s latency—cutting compliance research by ~4.5 hours per batch. Also developed LangChain-based agent workflows at Finta to automate CRM enrichment and investor lookup with strong testing, tracing (LangSmith), privacy guardrails, and auditability.”

“Technically oriented operator with experience driving a strategic migration to Microsoft Azure to modernize a company toward microservices and CI/CD, improving scalability and positioning for long-term optimization. Evaluates product ideas through an operational lens (efficiency, decision support, process optimization) and emphasizes building viable products with paying customers while maintaining revenue resilience.”

“Built and deployed a production RAG-based internal knowledge assistant that let analysts query company documents in natural language, using LangChain/LangGraph with Pinecone and a FastAPI service for integration. Emphasizes reliability in production through hallucination mitigation (retrieval tuning + prompt guardrails) and measurable evaluation/monitoring (accuracy, latency, task completion, hallucination rate), iterating based on user feedback.”

“At Inertia Systems, built a production LLM-powered ingestion pipeline that converts heterogeneous sources (PDF/JSON/IFC/SQL and financial tables) into standardized text and uses GraphRAG to construct a knowledge graph with verified dependency relationships. Also has hands-on HPC orchestration experience with SLURM, including creating a custom wrapper process manager to improve resource utilization under restrictive scheduling policies.”