Senior Full-Stack AI Engineer

Title: Full-Stack AI Engineer

Location: Remote (US). Travel required for project kick-offs.

About the Role:

Think of this as a Forward Deployed Engineer role, but truly remote. You'll be the technical lead on client engagements, working directly alongside Product Management and clients to understand the problem, decide on the right approach, and then go build it. When a new project kicks off you may travel on-site to get aligned with the client, but the day-to-day work happens from wherever you are. This is not a role where someone hands you a tech stack and a spec. You are the person making those calls. Maybe the client needs a full-stack TypeScript application. Maybe they need an agent-based system with Python, PydanticAI, and FastAPI. It depends on the client, and we meet them where they are. Postgres with pgvector? Milvus? Redis? Valkey? You evaluate what makes sense for this specific client, this specific problem, and you make the recommendation. You should be someone who opens Claude Code or OpenCode in the morning and ships working software by the end of the day. Some weeks that means solutioning with a client and a PM on a virtual whiteboard. Other weeks it means heads-down coding a full-stack application with AI woven into every layer. Most weeks it's both. You'll need opinions backed by experience, and the communication skills to explain those opinions to non-technical stakeholders in a room. Is this an agent problem or a workflow problem? Should we build a custom tool-calling pipeline or wire up an MCP server? You're the one making that call, defending it, and then delivering on it.

Responsibilities:

• Serve as the technical lead on engagements, interfacing directly alongside Product Management and clients. You own the technical direction.
• Make tech stack decisions based on client needs. Full-stack TypeScript for one project, Python with PydanticAI and FastAPI for the next. Postgres with pgvector here, Milvus or Redis/Valkey there. Every client is different and you figure out what fits.
• Build full-stack applications with AI integrated throughout, typically using TypeScript, Python, React, Next.js, FastAPI, and NestJS.
• Design, build, and deploy AI agents and agentic workflows using tool calling, RAG, and LLM orchestration. Know when agents are the right call and when they aren't. AI SDK and Pydantic AI are your bread and butter.
• Write code daily using agentic coding tools like Claude Code, OpenCode, or Codex. You treat these as real development tools, not novelties. Plan. Execute. Review.
• Lead code reviews and set technical standards for the team. The code that ships should be something you're proud of. No unread code gets shipped. No AI Slop.
• Manage and mentor engineers across distributed and offshore teams, helping them grow while keeping delivery on track.
• Work closely with project managers to scope work, manage timelines, and flag risks before they become problems.
• Build proof of concepts and prototypes quickly to validate ideas with clients before committing to full implementation.

Interested in remote work opportunities in Development & Programming? Discover Development & Programming Remote Jobs featuring exclusive positions from top companies that offer flexible work arrangements.

• Contribute to team building by helping hire, onboard, and develop engineers who share your standards.

Qualifications:

• 5+ years of full-stack development experience with TypeScript, Python, React, Next.js, and at least one backend framework (FastAPI, NestJS, or similar).
• Hands-on experience building with LLMs in production: agents, tool calling, RAG pipelines, prompt engineering, evals. Not just prototypes.
• Daily working experience with agentic coding tools (Claude Code, OpenCode, Codex, or Cursor). You should be faster with these tools than without them.
• Client-facing consulting experience. You've been in the room with stakeholders, presented technical recommendations, and delivered on them.
• Strong database modeling skills, particularly with PostgreSQL. You understand indexing, query performance, and schema design.
• Experience leading or managing small engineering teams (2 to 6 people), including working with offshore or distributed teams.
• Ability to own a project from solutioning through deployment. You don't need someone to hand you a spec; you can figure out what needs to be built and go build it.

Preferred Skills:

• Experience with agentic frameworks and orchestration patterns (PydanticAI, LangGraph, MCP servers, or custom implementations).
• Background in building AI-integrated products (not just internal tools) for external clients.
• Familiarity with vector databases (pgvector, Milvus, Pinecone) and retrieval-augmented generation patterns.

Browse our curated collection of remote jobs across all categories and industries, featuring positions from top companies worldwide.

• Experience writing evals and monitoring LLM quality in production.
• Published writing, open-source contributions, or community involvement in the AI engineering space.
• Project management experience or a track record of working closely with PMs to keep complex engagements on schedule.

Tech Stack (Example):

This is a representative stack. The actual tools and technologies vary by client and engagement.

• Agentic Coding: Claude Code, OpenCode, Codex, Cursor
• AI & Agents: LLMs (Claude, GPT, etc.), tool/function calling, MCP servers, RAG, PydanticAI, eval harnesses
• Languages: TypeScript, Python
• Frontend: React, Next.js (App Router), Tailwind CSS, shadcn/ui
• Backend: FastAPI, NestJS, Node, GraphQL
• Data: PostgreSQL, pgvector, Milvus, Redis/Valkey
• Cloud & Infra: Typically AWS, but could be Azure or GCP depending on the client. Docker, Vercel, CI/CD (GitHub Actions).

This isn't a "prompt engineering" role and it isn't a pure backend role that happens to touch an LLM. You'll be building real products for real clients, making hard technical decisions, and writing code every day. If you're the kind of engineer who loves figuring out the right solution to a messy problem and then actually building it, you'll fit in here.