Vetted FastAPI Professionals

Vishnu Priyan Sellam Shanmugavel

Screened

Mid-Level Applied AI Engineer specializing in LLM services, RAG, and OCR/NLP extraction

Arlington, VA4y exp

“Backend/platform engineer who built and evolved a large-scale healthcare document processing system (OCR + LLM orchestration) in Python/FastAPI on Google Cloud (Cloud Run, GCS, Firestore), processing ~1.5M files per batch and tens of millions overall. Emphasizes reliability and operational safety via deterministic IDs, idempotent state machines, strong observability, and self-healing reconciliation, plus disciplined migrations using dual-run validation and incremental rollouts.”

Revanth P

Screened

Mid-level DevOps Engineer specializing in AWS, Azure, Kubernetes, and GenAI infrastructure

Walnut Creek, CA4y exp

“Database/platform engineer with stronger hands-on experience in AWS and Azure than GCP, but able to speak credibly about cloud database architecture, automation, and reliability engineering. They led an on-prem MySQL to RDS/DynamoDB migration, built Terraform/Python-based zero-touch database operations, and described a performance incident where latency dropped from 2s to under 300ms while supporting 2x traffic.”

“Built and shipped Site Audit AI, a production multi-turn Claude-based agent that autonomously crawls websites, calls tools, and generates scored audit reports—reducing a manual 2-3 hour developer workflow to under 60 seconds. Also brings practical experience integrating inconsistent payroll/HR data across platforms like QuickBooks and Keka, with a strong focus on validation, fault tolerance, and resumable workflows.”

“Backend/AI engineer with deep healthcare experience building production Python microservices that turn raw clinical audio into structured notes and insights. They owned systems end-to-end across architecture, launch, monitoring, and incident response, with measurable impact including 40% lower operating costs, 22% better latency, and 99.9% uptime in a regulated environment.”

“Built an end-to-end agentic population health strategy copilot for healthcare leadership, turning broad chronic disease questions into structured, evidence-backed strategy briefs. Stands out for combining healthcare domain knowledge with production-grade GenAI implementation, including LangGraph orchestration, Databricks/MLflow deployment, human review, and quality gates focused on citations, metrics, risks, and safety.”

“Backend/AI engineer who built an enterprise RAG chatbot over 40,000+ technical documents, owning the system from ingestion and retrieval design through launch, optimization, and incident prevention. Stands out for treating LLM reliability as a data, retrieval, and observability problem—delivering 90%+ benchmark accuracy, ~50% fewer hallucinations, and major gains in lookup speed and latency.”

Narayan Anantha Krishnan

Screened

Junior AI/ML Engineer specializing in LLMs, RAG, and cybersecurity

Syracuse, NY2y exp

“AI/full-stack builder with hands-on experience shipping conversational and agentic products, including a travel itinerary assistant, a multi-agent data analysis platform, and a self-correcting RAG system. Also brings academic research depth from Syracuse University, where they helped develop tiny-LLM-based IoT threat mitigation and presented an accepted paper at FLAIRS 39.”

“Frontend-focused engineer with hands-on ownership of complex Angular UI architecture, browser performance optimization, and accessibility remediation. Notably led ADA compliance updates on a public-facing app by rewriting base components around semantic HTML, contributing to major sales wins.”

SIVA RAMAKRISHNA PALADI

Screened

Mid-level AI/Full-Stack Engineer specializing in agentic AI and RAG systems

Santa Clara, CA5y exp

“Solo builder who shipped two ambitious AI products from scratch: Zoly, a healthcare/pharmacy automation platform with voice agents, RAG, clinician dashboard, and patient app live in 4 months, and Breeth, a contextual memory system for AI agents deployed on AWS. Particularly compelling for teams needing a hands-on full-stack/AI engineer who can operate in ambiguity, design for safety and compliance, and turn complex agent workflows into production products.”

“New grad software engineer who has already built both a full-stack location-based social app and an internal AI on-call copilot using OpenAI and LangChain. Stands out for combining end-to-end product execution with practical LLM engineering, including RAG, fallback design, citations, and production evals, plus shipping a hackathon-winning MVP in 24 hours.”

“Software engineering intern who built and deployed a full-stack telemedicine platform (React/Node/MongoDB) used daily in a pediatric clinic, incorporating PyTorch-based predictive features. Demonstrated strong customer-facing iteration and production performance debugging—resolved a live slowdown by indexing/optimizing MongoDB queries and adding caching, improving response times by ~50%.”

“Student technologist building production-oriented AI products, including a college guidance chatbot for Track2College and a voice-based travel assistant. Strong hands-on experience with RAG systems, FastAPI backends, TypeScript frontends, retrieval evaluation, and tool-using LLM workflows, with a clear focus on grounded, reliable user experiences.”

“Built AI-powered products across both healthcare and financial services, including a privacy-conscious assistant for elderly health check-ins and a production RAG system for high-stakes financial document analysis. Stands out for combining full-stack engineering with strong LLM reliability practices—grounding, structured outputs, fallback handling, monitoring, and human-in-the-loop controls—while delivering measurable impact on accuracy, speed, and system performance.”

“Built and owned an internal AI-powered knowledge assistant that centralized fragmented company knowledge across docs, tickets, and internal systems. They designed the backend, ingestion pipelines, vector search, RAG workflow, and APIs, then drove adoption through pilot testing and quality improvements—ultimately automating roughly 30% of support inquiries and cutting resolution time by about two hours per ticket.”

“Backend engineer (Encore) who led the evaluation and redesign of a high-volume, low-latency real-time retrieval/ranking and inference platform on AWS, shifting from tightly coupled services to a modular architecture for better fault isolation and independent scaling. Strong focus on production reliability, observability, and security (JWT/RBAC, multi-tenant scoping, Postgres/Supabase RLS), with disciplined migration playbooks (feature flags, shadow traffic, dual writes/reconciliation).”

“Backend engineer who has led redesigns and migrations for a real-time logistics platform, improving scalability and resilience while managing eventual consistency tradeoffs. Demonstrates strong distributed-systems rigor (idempotency, transactions, async queues, monitoring) and builds secure, versioned FastAPI APIs with JWT/OAuth2, RBAC, and database row-level security.”

“Built a production multi-agent RAG assistant using LangChain/LangGraph with OpenAI embeddings and FAISS, focusing on retrieval quality and latency (Redis caching, parallel retrieval, precomputed embeddings). Experienced orchestrating ETL/ML pipelines with Airflow and Databricks Workflows, and has delivered an AI assistant for business ops to extract insights from policy/compliance documents through close non-technical stakeholder collaboration.”

“Built production LLM/agent systems for procurement and contract spend controls, including a proactive contract value leakage detection platform that moved an organization from reactive audits to pre-payment rejection. Combines multi-agent orchestration (Semantic Kernel/LangChain/AutoGen), document AI benchmarking (Textract vs Azure DI), and MLOps/testing (MLflow, QTest/Pytest) with strong security practices (RAG-grounded responses to prevent prompt injection). Integrated anomaly alerts directly into SAP SES workflows and Power BI dashboards, citing ~$38M leakage addressed across large spend environments.”

“Frontend engineer in fintech who led a client onboarding platform end-to-end, building a scalable React/TypeScript architecture with Redux-driven multi-step verification workflows. Strong focus on quality at scale through UI automation/E2E testing and CI/CD (GitHub Actions + Docker), enabling faster releases (bi-weekly to daily) while staying stable despite evolving backend APIs.”

“Product-minded full-stack engineer with hospitality tech experience who owned and scaled a multi-region guest verification/check-in workflow (ID/passport scanning, OCR, and government submissions) and built internal tools that cut manual entry up to 80%. Also built a React/TypeScript + FastAPI RAG “second brain” with async ingestion workers and an event-driven e-folio email microservice hardened with idempotency and retries.”

“Built and deployed production LLM applications including a natural-language-to-read-only-SQL system focused on ambiguity handling and query safety (schema whitelisting, intent validation, confidence checks, deterministic execution). Experienced with LangChain-based, modular agent orchestration and RAG document QA for large PDFs, with a metrics-driven testing/evaluation approach and cross-functional delivery with marketing on an AI content recommendation/search tool.”

“Built and owned a customer-facing Document Intelligence Service for legal contract analytics at Noasis Digital, delivering extraction/summarization with careful accuracy controls (confidence thresholds, versioned deployments, production logging). Also developed a React/TypeScript document review app and internal QA dashboard, and has hands-on microservices experience with async messaging (RabbitMQ), timeout tuning, and centralized structured logging for reliability at scale.”

“Built and deployed a production AI-powered personalized learning platform (Django + FastAPI) featuring an LLM+RAG tutoring assistant and automated grading. Demonstrates strong applied LLM reliability engineering (structured JSON outputs with Pydantic validation, hallucination control via FAISS-based RAG thresholds and refusals) plus scalable async microservice design and Airflow-orchestrated ETL across AWS/GCP.”

“Master’s capstone at Stevens: conceptualized and helped build a cross-platform assistive mobile app for visually impaired users with currency detection (ML), voice-driven AI chatbot (OpenRouter), and a guided navigation video-call feature using a shared room code. Personally implemented Firebase login/sign-in, facial-recognition login, video calling, chatbot integration, and led integration/testing across the full app.”