Remote
Contract
Big Tech experience (Amazon, Google, Meta, Apple, Microsoft, Netflix, …), Top University degree (can be local)
Skills: Typesrcipt/Node, Python, LLM/Agentic work in production
We are looking for a hands-on full-stack engineer to help build AI-native data and platform capabilities that power product and frontend experiences. This person should be comfortable owning work end to end across backend, data, AI/LLM integrations, and frontend when needed. The role has a clear backend lean, so we do not need expert-level frontend depth, but the person should have enough React experience to expose, review, or operationalize data through practical user-facing or internal workflows. This is an hourly contract role, full-time hours, remote, with a minimum of 4 hours of daily overlap with New York working hours, and continuation tied to delivery against agreed milestones.
What you will work on
You will help design and build systems that use LLMs, vision models, retrieval, and evaluation workflows to extract, structure, and reason over data. The work includes backend services, data pipelines, internal tools, and production systems that make extracted data available downstream in a grounded, predictable, and reliable way.
You may work on areas such as:
• LLM-powered extraction from documents, including multilingual and historical material
• Vision-model-based extraction from images and documents
• Systems that ground model outputs in trusted structured context, where every claim traces to its evidence
• Retrieval workflows, context assembly, and answer grounding
• Evaluation datasets, scoring workflows, and regression checks, so quality is measured rather than asserted
• Internal tools for human review and verification of AI-generated outputs before they reach production
• Production-grade AI workflows with observability, latency, cost, retries, queues, and failure handling React-based internal and reviewer-facing surfaces when needed
Technology
• We use TypeScript/Node as the primary language, and we are looking for production experience with Postgres, and working experience with React.
• LLM and vision-model integration via APIs, provider-agnostic, we care that you have shipped against frontier-model APIs and built evals around them.
• Serverless or edge experience (Cloudflare Workers, Lambda class) for the deployment model.
• Python for eval harnesses and data tooling, Supabase specifically.
• AI-native development practice, working with coding agents rather than alongside them
Required experience
• 7+ years of professional software engineering experience
• Strong full-stack experience with a backend lean, building production services, APIs, and data pipelines
• Working React experience
• Real experience using LLMs and vision or multimodal models for data extraction, structured reasoning, classification, or entity extraction
• Experience grounding model outputs in trusted data, structured context, or retrieved information
• Demonstrated eval discipline: you have built evaluation datasets, scoring workflows, and regression checks, not just prompts
• Ability to reason about model failure modes and improve the system around the model
• Strong product and execution judgment; pragmatic version first, no over-platformizing
• Ability to work independently from problem definition to shipped system
Nice to have
• OCR, document understanding, or image-to-structured-data workflows
• Embeddings, vector search, or hybrid retrieval
• AI agents or tool-using LLM systems
• Consumer, marketplace, commerce, or data-rich product environments
Thanks & Regards,
Navneet Singh
Senior Talent Acquisition Specialist
Fast Hire Inc.
