Senior Full-Stack Engineer, Applied AI , NY

Manifest OS is an AI-native company on a mission to replace the billable hour and make legal services more accessible for American businesses and consumers. We power the next generation of AI-native law firms with one unified global brand, a proprietary technology platform, and a centralized back office — enabling lawyers to eliminate the administrative burden and focus on delivering exceptional outcomes for their clients.

Backed by leading venture investors, Manifest O.S. is scaling rapidly.

Our engineering team move fast and own their work end-to-end. We're building AI-powered products that customers actually use every day, not demos that look impressive in screenshots. The team values shipping over perfection, clear communication over process, and learning from real user feedback over theoretical debates.

You have 5-8 years of full-stack development experience with a track record of shipping production software. You're fluent in Type Script and React on the frontend, and you're comfortable with either Python or Node.js for backend development. Most importantly, you've built production systems using LLM APIs — not just weekend projects, but systems that handle real traffic and real user expectations.

You understand the difference between getting an AI demo to work once and building something reliable enough to put in front of customers. You've probably dealt with rate limits, prompt injection attempts, inconsistent model outputs, and the challenge of building UIs around non-deterministic systems. You know when to use streaming responses and when they're overkill, and you've thought seriously about how to test and monitor AI-powered features.

Experience with structured output handling, evaluation frameworks, or observability tools for AI systems would be valuable but isn't required. What matters most is that you approach AI engineering with the same rigor and user focus that you'd bring to any other production system.

We're looking for a senior full-stack engineer to own AI-powered features from conception to production. You'll be working on customer-facing products where the AI isn't just a novelty — it's doing real work that people depend on. This means you'll spend your time thinking about prompt reliability at scale, building interfaces that make AI feel natural rather than magical, and solving the unglamorous but critical problems that separate demos from products.

The role sits at the intersection of traditional software engineering and the unique challenges of AI systems. You'll architect backend services that orchestrate multiple models, handle streaming responses gracefully, and degrade gracefully when things go wrong. On the frontend, you'll build interfaces that give users confidence in AI outputs and make complex AI workflows feel simple. Success here means shipping features that customers love and that work reliably s is a high-autonomy role for someone who thrives in ambiguous environments.

You'll have significant input into product decisions and technical architecture. We need someone who can take a rough product idea, figure out what's actually feasible with today's AI capabilities, and build it in a way that feels polished and reliable to end users.

You're excited by the challenge of making AI systems reliable enough for real users. You enjoy the problem-solving aspects of working with non-deterministic systems and aren't frustrated by the inherent unpredictability of AI outputs. You're comfortable making technical decisions with incomplete information and iterating based on user feedback rather than trying to perfect things in isolation.

You have strong product instincts and can balance technical…