Vetted Distributed Systems Professionals

“At PwC, built and productionized an agentic RAG enterprise search assistant over 6M internal documents (8M embeddings), deployed across AWS and GCP. Drove major retrieval gains (72%→92% precision via BM25+dense hybrid with RRF and cross-encoder re-ranking), reduced hallucinations 30%, achieved <2s latency at 50–60K queries/month, and cut support tickets 30%—boosting adoption to 2,500 users by adding source-cited answers.”

“Backend engineer with hands-on ownership of Python/Flask microservices and recommendation systems across edtech and telecom. Deployed and operated real-time personalization/recommendation platforms on AWS EKS with Jenkins-based CI/CD, GitOps-style declarative configs, and strong observability practices. Has migration experience moving legacy mixed environments to modern containerized Kubernetes and built Kafka pipelines feeding ML services while managing schema evolution.”

“Backend/AI engineer with healthcare domain experience who built a patient journey analytics API (FastAPI/PostgreSQL/Snowflake/Redis) and debugged peak-hour latency down from ~900ms to ~50ms via indexing and query optimization. Shipped an LLM-powered clinical summary/recommendation assistant end-to-end and designed a multi-step risk evaluation agent workflow with safety guardrails against hallucinations and unsafe outputs.”

“LLM/agentic systems practitioner who specializes in moving customer prototypes into production within microservices environments, emphasizing reliability, latency, security, and measurable success metrics. Experienced in real-time troubleshooting using logs/traces and in enabling adoption through hands-on developer workshops (including live coding in Java Spring Boot) and pre-sales POCs that address technical objections and integration risk.”

“Built and productionized an LLM-enabled system visualization web app at Longshot, designed modularly to pivot quickly to a mobile-friendly interface as customer needs changed. Experienced in diagnosing LLM/agentic workflow failures using observability, deterministic replay, and fault-tree root cause analysis. Also delivers developer-focused demos and trainings (including robotics deployment/mapping at Meta) and partners with sales as a technical closer, including for government clients by demonstrating failure modes and system modularity.”

“At Esri, the candidate is building a production LLM-powered WebGIS AI framework that embeds an AI assistant into web maps and routes natural-language requests into ArcGIS JavaScript SDK functions via a LangGraph-orchestrated, multi-agent system. They emphasize production reliability and scale (strict tool calling/JSON, live schema validation, query guardrails) and rigorous evaluation/observability using LangSmith, offline prompt datasets, and latency/tool-call accuracy tracking.”

“Robotics software engineer focused on low-compute navigation/SLAM: built a 6-DOF SLAM validation pipeline (IMU + 2D LiDAR + ultrasonic) producing ~1cm OctoMap accuracy and deployed it on an Intel Atom by optimizing particle-filter SLAM with a greedy max-likelihood update. Deep ROS 2 experience (executors, composable/lifecycle nodes, QoS, timestamping) plus simulation and deployment tooling (Gazebo C++ plugins, Docker, CI/CD, ROS 2 build farm) and drone navigation work with MAVROS/PX4.”

“Backend engineer with deep experience building event-driven logistics systems (orders, warehouse execution, real-time delivery tracking) using Spring Boot/PostgreSQL/Redis and strong observability (Prometheus/Grafana). Led a zero-downtime migration from monolithic MySQL to a sharded architecture for ~2M users with dual-write, checksum validation, and fast auto-rollback, and has strong security expertise including PostgreSQL RLS for multi-tenant SaaS and robust OAuth/JWT handling.”

“Backend/AI engineer at Intuit who built a production AI-powered case assistant for support agents (FastAPI on AWS EKS) combining Postgres case data, OpenSearch retrieval with embedding reranking, and internal LLMs. Improved peak-season reliability by diagnosing P95/P99 timeout spikes and cutting P95 latency from ~800ms to <400ms via composite indexing, keyset pagination, connection pool tuning, and caching, while adding grounded-generation guardrails (evidence packs, confidence thresholds, fallbacks, human-in-the-loop).”

“Bank of America engineer/product owner who built a real-time transaction insights and spending categorization platform using React/TypeScript and Spring Boot microservices with Kafka. Deep experience in event-driven architectures, performance tuning at peak banking loads, and reliability patterns (SLOs, observability, feature flags, DLQs). Also created an internal monitoring/alerting tool adopted across engineering and ops, cutting incident response time by 40%+.”

“Built a production LLM-driven personalization microservice for realtor.com using LangChain/LangSmith with an MCP tool layer and RAG to generate schema-constrained ranked listings in real time, replacing a rule-based engine and improving engagement/lead conversion. Also owned an ambiguous cross-channel identity initiative, implementing an identity graph via Twilio Unify with required SDK and data-warehouse integration.”

“Backend engineer with PayPal experience building a high-reliability onboarding API platform (Java/Spring Boot) integrating KYC/compliance and serving 1M+ users annually. Also shipped an internal LLM-driven developer tool that automates PR review insights and OpenAPI documentation with rigorous evaluation, schema-bound guardrails, and production observability.”

“Data engineer who has owned end-to-end production pipelines ingesting ~500GB/day from APIs/databases/Kafka into an S3 data lake (Glue/Spark) with Airflow-orchestrated Great Expectations quality gates. Built resilient external data collection systems with idempotent jobs, exponential-backoff retries, raw data capture, and backfills; also shipped Snowflake-backed APIs with caching, versioned endpoints, and backward-compatible data contracts. Led an early-stage Azure data platform build with phased delivery and GitHub Actions CI/CD, resolving schema-mismatch incidents quickly without downstream corruption.”