Senior/Staff Backend Engineer, Applied AI

Fora•New York City, NY

9h•Hybrid

About The Position

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.

Requirements

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

Nice To Haves

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

Responsibilities

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