AI Developer

RAVE Aerospace is redefining the in-flight experience through innovative entertainment and connectivity solutions trusted by airlines around the world. We combine advanced hardware, intelligent software, and connected digital platforms to help airlines create more engaging, seamless, and reliable passenger experiences. As the future of air travel evolves, RAVE is building the technology that keeps passengers connected from takeoff to landing.We are seeking an experienced AI Developer to design, build, and scale production AI applications and autonomous agents on a modern, self-hosted platform. This role will play a key part in shaping the architecture, tooling, and engineering standards that power AI capabilities across the organization. Working across the full technology stack, the AI Developer will leverage large language models and AI coding agents as core components of the development process to deliver reliable, high-impact solutions. This is a highly influential, hands-on engineering role focused on building practical, production-ready AI systems in a fast-moving and collaborative environment.This individual is equally comfortable discussing architecture and implementing solutions, with a strong sense of ownership and a desire to influence platform direction, tooling decisions, and engineering best practices. They are curious, adaptable, and energized by solving complex problems while building scalable, maintainable systems. Strong collaboration and communication skills are essential, as this role partners closely with technical and cross-functional teams to bring AI capabilities into production.ResponsibilitiesDesign and implement AI-powered services, agents, and internal applicationsBuild and maintain MCP (Model Context Protocol) servers that expose enterprise systems to LLM clientsDevelop end-to-end features — backend services, data pipelines, and user-facing UIs — using agent-assisted workflowsDesign retrieval pipelines (chunking, embeddings, vector search) and prompt strategiesIntegrate LLMs across managed and self-hosted runtimes, choosing the right tool for cost, latency, and privacy constraintsInstrument prompts and agents with traces, evals, and regression checksEnforce shared platform conventions: authentication, RBAC, container networking, secrets handlingMentor other engineers on applied AI patterns and on getting the most out of agentic coding toolsRequirementsRequired Skills & Experience10+ years of experience in software engineering2+ years working directly with AI/ML or LLM-based applicationsStrong software engineering fundamentals) — systems thinking, debugging, API design, data modelingProduction experience shipping web services and/or data products in any modern stackDemonstrated fluency with AI coding agents (Claude Code, Cursor, Copilot, Aider, or similar) as part of daily workPractical experience integrating LLMs into real products (any major provider)Working knowledge of retrieval-augmented generation (RAG): embeddings, vector search, chunking strategiesSolid SQL and relational data modeling skillsComfortable with containerized development (Docker / docker-compose)A pragmatic approach to tests, observability, and operational qualityPreferred ExperienceHands-on experience with any of the following:Model Context Protocol (MCP) — building servers and/or clientsManaged LLM platforms (Bedrock, Anthropic, OpenAI, Azure OpenAI)Self-hosted LLM runtimes (Ollama, vLLM, llama.cpp)Production vector databases (Qdrant, pgvector, Weaviate, Pinecone)LLM observability and eval tooling (Langfuse, LangSmith, Phoenix, etc.)Workflow orchestration (Prefect, Airflow, Dagster)Modern frontend work (React or similar) for building internal tools and agent UIsSSO / OIDC and role-based access control patternsPrompt engineering and structured-output techniques (tool use, JSON schema, function calling)Experience operating GPU workloads on LinuxPrior technical leadership or tech-lead experience on AI / data productsDevelopment EnvironmentSelf-hosted Linux platform with GPU acceleration for local model inferenceContainerized services with shared internal networkingAI coding agents available and encouraged for day-to-day developmentLocal-first development with simple bypasses for auth and external dependenciesFocus on simplicity, observability, and reproducibility over framework sprawlWhat We're Looking ForAn applied AI engineer who ships — comfortable owning a feature from prompt design through production rolloutSomeone who treats LLMs as one component in a system, not the whole system — strong fundamentals in APIs, data, and infrastructureAn engineer who is genuinely fluent with agentic coding tools and can demonstrate how they use them to multiply their outputA pragmatic builder who values evals, traces, and clear contracts over framework magicA collaborator who can translate fuzzy stakeholder requests into concrete agent and application designsBenefitsThe base salary range for this position is $150,000-200,000 per year and reflects multiple levels within the role. Final level and compensation will be determined based on the candidate's skills, experience, qualifications, and internal equity.In addition to a comprehensive package of health benefits that include company contributions, RAVE Aerospace offers a variety of additional benefits and perks to enhance your work-life balance experience including but not limited to:A home allowance to elevate your home workspaceDiscretionary bonus programFuture financial security with a 401(k) program with company matchPaid time off covering vacations, personal time off and sick days, capped off by an exciting year-end holiday shutdownEmbraced flexibility with our alternative work schedule (9/80) to navigate your workweeks with every other Friday off