Python Full stack AI Lead - Only W2

We are not considering C2C candidates for this role. The candidate must be willing to work on our W-2 from day one.

Position:- Full stack Ai Lead

Location:- Princeton, NJ

Onsite / Hybrid

Client need 10+ yr exp What are the top 3 skills required for this role?

• GenAI & Spec-First Development — deep expertise in spec-driven workflows (GitHub Spec Kit or equivalent), AI agent orchestration, and building AI-powered product features end to end.
• Full Stack Engineering (React / Node / Python) — extensive experience delivering production applications across the entire stack, from modern React UIs to Node.js and Python backends with robust API layers.
• Cloud & Data (AWS + MongoDB / PostgreSQL) — strong command of AWS infrastructure and both relational and document databases, including schema design, optimisation, and cloud-native deployment patterns.

Job Description/ Responsibilities

• Drive spec-first development practices across teams — leading the authoring of specs, technical plans, and agent-ready task breakdowns using GitHub Spec Kit or equivalent tooling before any code is written.
• Architect and build full stack web applications using React and modern JavaScript / TypeScript frameworks on the frontend, backed by Node.js and Python services.
• Design, develop, and maintain RESTful and GraphQL APIs — ensuring performance, reliability, versioning, and security across all service boundaries.
• Lead cloud architecture and deployment on AWS, leveraging services such as Lambda, EC2, S3, API Gateway, RDS, and CloudFormation for scalable, resilient systems.
• Integrate and build AI-powered features using LLMs, AI agents, and prompt engineering techniques, translating GenAI capabilities into tangible product value.
• Own data architecture decisions across MongoDB and PostgreSQL, including schema design, indexing strategies, query optimization, and migrations.
• Mentor and technically guide engineers at all levels, conducting code reviews and raising the overall engineering bar across the organization.
• Partner with product, design, and AI/ML teams to define requirements and translate them into well-specified, high-quality software.
• Contribute to engineering strategy, tooling choices, and cross-team standards as a senior technical leader.

Required Qualifications

• 12+ years of professional software engineering experience with a strong full stack background.
• Proven experience with GenAI tools and a spec-first development approach — including GitHub Spec Kit, AI agent frameworks, or equivalent spec-driven methodologies.
• Expert-level proficiency in React and modern JavaScript / TypeScript frameworks (Next.js, Vue, or similar).
• Strong backend development experience with both Node.js and Python — building, maintaining, and scaling production-grade REST and GraphQL APIs.
• Deep, hands-on experience with AWS — comfortable across core services (Lambda, EC2, S3, API Gateway, RDS) as well as security, networking, and cost optimization.
• Solid experience designing and managing both MongoDB (document store) and PostgreSQL (relational) databases at scale.
• Demonstrated ability to integrate LLM APIs (OpenAI, Anthropic, or similar), build prompt engineering pipelines, and deliver AI-augmented product features.
• Track record of leading technical delivery — setting architecture direction, unblocking teams, and owning outcomes across complex, multi-service systems.
• Bachelor’s or master’s degree in computer science, Engineering, or equivalent practical experience.

Good to Have

• Experience with GitHub Copilot, Cursor, or AI-assisted development environments integrated into day-to-day engineering workflows.
• Familiarity with containerization (Docker, Kubernetes) and infrastructure-as-code tools (Terraform, AWS CDK).
• Exposure to vector databases (Pinecone, pgvector) or RAG (Retrieval-Augmented Generation) pipeline design.
• Experience with AI orchestration frameworks such as LangChain or LlamaIndex.
• Knowledge of event-driven architecture patterns using AWS SQS, SNS, or EventBridge.
• Familiarity with MLOps practices and deploying ML models into production pipelines.
• Contributions to open-source projects, technical writing, or a portfolio of AI-integrated applications.