Vetted Workflow Orchestration Professionals

“Backend owner at Apple for an AI workflow orchestration service, with hands-on experience stabilizing peak-traffic production systems using OpenTelemetry-style tracing, bounded async concurrency, and database performance tuning. Built and shipped a Python LLM-agent orchestration layer to automate multi-step operational workflows, emphasizing guardrails, auditability, and deterministic fallbacks to keep non-deterministic AI behavior production-safe.”

Muhan Zhang

Screened

Junior AI Software Engineer specializing in LLM pipelines, OCR, and RAG

Palo Alto, USA2y exp

“Built and shipped a production LLM pipeline for nursing home Medicare reimbursement (PDF OCR + fact extraction + keyword RAG + QA) that reportedly increased payouts by ~$1K/month per patient. Strong in LLM ops/benchmarking (ground truth, LLM-as-judge, cost/I-O tracking) and pragmatic optimization—swapped retrieval approaches, fine-tuned a small model to cut OCR cost 90%, and migrated workloads to Azure/Temporal to scale nightly processing 10x.”

Jingyao Chen

Screened

Junior Backend/Platform Engineer specializing in AI microservices and cloud-native systems

Pittsburgh, PA2y exp

“Cofounder at MeowyAI who shipped a production multimodal (vision/voice/text) AI task manager using Gemini, tackling real-world issues like hallucinations, tool-calling safety, and RAG-based preference memory. Also built a production multi-agent RAG system orchestrated with LangGraph (and contributes to LangChain), with strong emphasis on latency optimization, observability (OpenTelemetry), and rigorous testing/evaluation including A/B tests and adversarial prompting.”

Asrith Velireddy

Screened

Mid-level AI/ML Engineer specializing in MLOps, LLMs, and scalable ML systems

Harrison, NJ4y exp

“ML/LLM engineer at Adobe who deployed a transformer-based personalization and campaign-targeting recommender system end-to-end, including PySpark/Airflow pipelines processing 12M+ events/day and containerized inference on AWS SageMaker (Docker/Kubernetes). Also has hands-on LLM workflow experience (RAG, semantic search, prompt optimization, hallucination mitigation) with a metrics-driven approach to reliability, drift monitoring, and reproducible retraining via MLflow.”

Jehanzeb Khan

Screened

Director-level Engineering Manager specializing in large-scale data and compute platforms

Sunnyvale, CA20y exp

“Platform and distributed-systems leader (player-coach) who owned architecture and reliability for an Amazon analytics/data platform serving ~100K internal users at exabyte scale. Built an ML-driven “Lakeflow” optimization layer that cut pipeline completion times ~20–25% and reduced compute waste >15%, and led major incident response/redesign efforts (e.g., deletion storm) with strong rollout/observability/rollback practices.”

“Technical lead who shipped a production GPT-4-powered customer support agent for Square, serving a large fintech customer base through a React chat interface with tool-using orchestration, guardrails, and live handoff paths. Brings strong real-world experience in agent reliability, evaluation, observability, and workflow orchestration using Temporal, Sidekiq, Pinecone, Datadog, and Snowflake.”

“Operations leader with Amazon experience owning a founder-level initiative during national supply chain Regionalization, building and scaling a "Stack-to-Light" operating mechanism to standardize non-sortable FC execution with instrumentation and balanced-scorecard metrics. Later joined Revivn to stabilize an underperforming operation by developing frontline leaders and aligning ops with finance and GTM through clear KPIs and operating cadence.”

“AI/LLM-focused engineer with hands-on experience building RAG pipelines, prompt engineering workflows, and multi-agent systems using tools like LangChain. Stands out for combining AI-assisted development with production-grade validation and for leading the architecture/orchestration of agent-based recommendation systems that improved response time, accuracy, and scalability.”

“Backend/data engineer who has owned production Python APIs and high-throughput async workflows on AWS (FastAPI, Docker, ECS/EKS/Lambda) with mature reliability practices like idempotency, bounded retries, circuit breakers, and strong observability. Also built AWS Glue ETL into an S3/Redshift lakehouse and modernized legacy batch systems via parallel-run parity testing and feature-flagged migrations, including a SQL tuning win cutting a multi-minute query to under 10 seconds.”

Sandeep Rohilla

Screened

Principal Platform Engineer specializing in AI-driven document automation

San Francisco, CA20y exp

“Backend engineer who built an event-driven, multi-service resume review system integrating AI/ML workflows. Demonstrated strong performance engineering (e.g., composite indexing dropping latency from ~600ms to ~35ms and major P95 gains) and high-throughput pipeline optimization via caching, batching, and worker concurrency tuning, with multi-tenant isolation implemented across DB and Redis.”

Michael Kilgore

Screened

Mid-Level Software Development Engineer specializing in AWS data pipelines and forecasting systems

3y exp

“Built and deployed (via an Upwork contract) an LLM-powered agent for options trading that detects large options trade events, enriches them with market/filing data (price history, earnings transcripts, insider trading), and delivers recommendations via Telegram. Implemented schema-constrained outputs (Pydantic/Google GenAI), robust orchestration, logging, and error-notification handling, plus vector-DB-based reuse of prior outputs to improve consistency.”

“Engineer using AI deeply in real production workflows, not just for code generation: they built agents for PR reviews and incident debugging that reportedly reduced review time by 50% and sped root-cause analysis by 30%. They also designed a three-agent personalization pipeline for real-time navigation curation, showing hands-on experience with multi-agent systems, orchestration, and rule-based refinement.”

“Built and shipped a map-embedding SDK (published to npm) for Walmart apps, solving key performance issues with real-time streaming (WebSockets) and Canvas rendering while prioritizing developer experience. Also applies LLM/agentic patterns in production workflows—using diagnostic agents and human-in-the-loop escalation to detect and resolve issues (e.g., voice agent loops caused by RAG API failures). Has sales-engineering experience supporting enterprise renewals, including a million-dollar contract renewal while at Siemens working with Ford stakeholders.”

“Second most active contributor at Daice Labs, owning a production AI-powered software development collaboration platform’s end-to-end execution infrastructure (TypeScript/Next.js backend, Node.js CLI, shared libs). Built the full multi-agent pipeline (planning/codegen/summary), Supabase-backed context assembly and realtime state, Git/GitHub automation, and a provider-agnostic LLM abstraction with strict Zod validation and retries, backed by extensive tests and design specs.”

Hansraj Pabbati

Screened

Senior Software Engineer specializing in AI/LLM systems and cloud backend platforms

Remote, CA8y exp

“Built and owned an end-to-end AI-powered natural-language-to-SQL deployment within Oracle OCI/Autonomous Database, including enrichment pipelines, RAG-based retrieval, SQL generation APIs, and post-launch monitoring. Stands out for combining LLM production engineering with strong guardrails, stakeholder management, and operational rigor around accuracy, latency, hallucination mitigation, and reliability.”