> Markdown version of [/jobs/ext/457341-senior-staff-backend-engineer-applied-ai](https://www.wearedevelopers.com/jobs/ext/457341-senior-staff-backend-engineer-applied-ai). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Senior/Staff Backend Engineer, Applied AI - **Company:** POZTO, INC. - **Location:** New York, NY, United States (Remote available) - **Experience:** Expert - **Salary:** $155,000.0 - $225,000.0 - **Contract:** Permanent contract - **Skills:** Clean Code Principles, Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Relational Databases, Web Development, Django Web Framework, Python (Programming Language), Systems Development Life Cycle, RabbitMQ, Data Streaming, Data Logging, Flask (Web Framework), Large Language Models, Prompt Engineering, Backend, AI Platforms, Kubernetes, Information Technology, Low Latency, Celery, Front End Software Development - **Published:** June 6, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=46bc8314d007eb17 ## About the Role Do you have experience in System design for system development?, Do you have a Bachelor's degree?, * Bachelor's Degree in Computer Science, or equivalent practical experience * 5+ years experience in backend web development * 3+ years experience with Python, using Django / Flask / Alternative * High API and distributed-systems design skills, with strong fundamentals in relational databases and ORMs * Genuine curiosity and drive to go deep and stay up to date on applied AI * Ability to be a team player, with strong communication and collaboration skills * An entrepreneurial mindset and comfort with ambiguity and fast iteration Strongly Preferred * Hands-on experience shipping LLM-powered features in production: MCP tools, agentic loops, structured outputs, streaming (SSE), prompt design, retrieval, evals * Familiarity with the modern agent stack: the Model Context Protocol (MCP), LLM provider SDKs (e.g., Anthropic, OpenAI), and agent / eval frameworks * Experience designing evaluation and observability for non-deterministic AI systems (offline evals, LLM-as-judge, tracing, prompt / version tracking) * Daily use of AI coding tools as part of how you build * Experience with async task and streaming infrastructure (Celery, RabbitMQ, or similar) * AWS experience * Kubernetes experience ## Description We're looking for a seasoned Senior / Staff Backend Engineer to help build Fora's fast growing suite of AI-driven products and infrastructure. Our ideal candidate is someone who follows AI closely and can tell which models and frameworks are worth using and which won't last; has built, shipped, triaged, and optimized something that uses LLMs (in production or on the side); and has experience working in ambiguity, on top of APIs and SDKs that change every few weeks. Most travel agents can't scale past $1M / year in business before they need to make their first hire. By giving advisors a day-one assistant to delegate entire workflows to, we believe they should be able to solo-operate $100M / year businesses. Our current focus is on building Via, an AI co-pilot built into our advisor portal. Via takes on time-consuming tasks so advisors can move faster, stay more organized, and glean insights into their business that they couldn't ever before, freeing them to do what they love: building client relationships, curating unforgettable trips, and growing their business. This role tackles challenges across the AI stack including: Building and expanding our suite of MCP tools; tuning our agent harness and orchestration layer for quality, cost, and speed; and building evaluations and observability that let us ship changes to a non-deterministic system with confidence; and much much more., * Partner with the team's Product Manager and Designer to define and prioritize Fora's Applied AI roadmap, turning ambiguous goals into shippable agent capabilities * Help design and build our MCP tooling - exposing Fora's data and service layers through permission-aware MCP tools that agents can call on an advisor's behalf, with the proper guardrails in place so that we only ever act on the right data at the right time * Build and harden our agent orchestration - tool-calling loops, streaming responses, multi-step workflows, retries and guardrails, and the contracts between Fora's advisor portal and the AI service * Continue improving the reliability of a non-deterministic system by designing evals, regression suites, tracing, and logging event metrics so we can measure quality, catch tool-call drift, and ship prompt, model, and tool changes with less risk * Focus on performance, latency, architecture, and clean code - advisors feel every millisecond of a streamed response and every wrong tool call * Collaborate with engineers across the company to define end-to-end solutions that span the AI services, the core Django platform, and our portal frontend Take features from 0 * 1, owning an entire solution from design to implementation to delivery and beyond * Help establish the patterns, primitives, and best practices for Applied AI at Fora as the teams surface area grows ## Related Videos - [Celery on AWS ECS - the art of background tasks & continuous deployment](https://www.wearedevelopers.com/videos/561-celery-on-aws-ecs-the-art-of-background-tasks-continuous-deployment) - [Developing the Backend with Stefan Lingler, CTO at Shpock](https://www.wearedevelopers.com/videos/100360-developing-the-backend-with-stefan-lingler-cto-at-shpock) - [Beyond Kafka & RabbitMQ: Why NATS is the Future of Microservices Messaging](https://www.wearedevelopers.com/videos/1646-beyond-kafka-rabbitmq-why-nats-is-the-future-of-microservices-messaging) - [Building Agentic Applications: A Deep Dive into Zooka, an AI Cardiologist Assistant](https://www.wearedevelopers.com/videos/2030-building-agentic-applications-a-deep-dive-into-zooka-an-ai-cardiologist-assistant) - [Why Systems Break After Initial Success: The Architectural Failures That Take Months to Surface](https://www.wearedevelopers.com/videos/2048-why-systems-break-after-initial-success-the-architectural-failures-that-take-months-to-surface) - [Nest.js - TypeScript in the backend can also be clean](https://www.wearedevelopers.com/videos/1033-nest-js-typescript-in-the-backend-can-also-be-clean) ## Related Articles - [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline) - [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development) - [Dev Digest 137 - AI'm not sure about this](https://www.wearedevelopers.com/magazine/485-dev-digest-137-ai-m-not-sure-about-this) - [From Prototype to Production: Build AI Agents with This Free 4-Course Learning Path](https://www.wearedevelopers.com/magazine/655-from-prototype-to-production-build-ai-agents-with-this-free-4-course-learning-path) - [Dev Digest 132 - Binging WADFlix?](https://www.wearedevelopers.com/magazine/473-dev-digest-132-binging-wadflix) - [Dev Digest 120 - Apple and peers](https://www.wearedevelopers.com/magazine/455-dev-digest-120-apple-and-peers)