About RouteGenie
RouteGenie is a US-based SaaS platform serving the Non‐Emergency Medical Transport (NEMT) industry across North America.
Our software powers dispatch, routing, billing, and operations for hundreds of transportation providers moving millions of medically vulnerable passengers every year.
AI is a strategic priority for us.
We believe agentic systems will materially change how dispatchers, schedulers, and operators do their work, and this role exists because we want a strong engineer to help us build that future inside our product.
The Role
You will design and ship agentic workflows and LLM‐powered features inside the RouteGenie product — dispatcher copilots, intelligent routing assistants, document and intake automation, and customer‐facing voice and chat agents.
You'll also build internal‐operations agents that accelerate our own marketing, sales, support, and back‐office workflows.
As RouteGenie's first dedicated AI engineer, you'll propose the patterns, recommend the tools, and shape how we measure quality.
You will sit on the LatAm Hub engineering team in Mexico and work daily with European‐based Engineering and US‐based product and operations stakeholders.
What This Role Is Not
Not a foundation‐model research role, not a pure ML or data‐science role, not a general backend role that occasionally touches AI.
AI features will be your full‐time focus.
Key Responsibilities
Architect and ship agentic workflows and LLM‐powered product features: handling planning, memory, state management, tool orchestration, guardrails, human‐in‐the‐loop checkpoints, and voice/chat interfaces.
Partner with leadership: collaborate with product and engineering leadership during feature ideation and scoping.
Provide pragmatic input on level of effort, technical feasibility, and realistic likelihood that proposed AI approaches will work in production versus remain demo‐grade.
Design retrieval architectures: choose between vector retrieval, long‐context/cache‐augmented, tool‐based agentic retrieval, graph‐based, or hybrid approaches.
Avoid one‐size‐fits‐all retrieval.




Establish evaluation systems: build systems that prove AI features actually work.
Define accuracy, correctness, safety metrics; assemble test datasets; pre‐release benchmarks; monitor production quality to catch regressions when models, prompts, or data change.
We do not ship LLM features we cannot measure.
Production hardening: integrate AI features into existing stack and harden for production—managing APIs, latency and cost budgets, prompt versioning, observability, PII/PHI safety while working alongside platform and product engineers.
Internal operations pipelines: build agentic pipelines for internal operations—automating marketing, sales, support and back‐office workflows where AI agents accelerate manual effort.
Team enablement: educate and enable broader engineering team to incorporate agentic flows into features they build.
AI capabilities woven into normal product work across the team, not siloed.
Development championship: champion AI‐assisted development practices across the LatAm Hub engineering team.
What Success Looks Like
First 90 days: form working point of view on right model and execution environment, stand up evaluation and observability scaffolding, ship one small production AI feature with documented quality methodology.
By the end of year one: ship 3–5 AI features in production with measured quality and regression strategy that survives model and prompt updates; at least one internal‐operations agent live and measurably reducing manual effort; be go‐to engineer for AI questions.
Technology Stack
LLM Providers & APIs Anthropic Claude (primary), OpenAI, AWS Bedrock
Local / Self‐Hosted LLMs Ollama, LM Studio, llama.cpp, vLLM; open‐weight model families (Llama, Qwen, Mistral,



etc.)
Agent Frameworks LangChain / LangGraph, LlamaIndex, OpenAI Agents SDK, or equivalent
Retrieval & Knowledge Vector databases (Pinecone, Weaviate, pgvector); RAG, cache‐augmented generation, tool‐based agentic retrieval, GraphRAG, hybrid approaches
Voice AI ElevenLabs, VAPI, LiveKit, Deepgram
LLM Observability & Eval LangSmith, Braintrust, Phoenix, Helicone, or similar
AI‐Assisted Development Claude Code
RouteGenie Stack Python, Django, PostgreSQL, Angular, TypeScript
Qualifications & Requirements
3+ years software engineering experience.
1+ year hands‐on production LLM / AI features shipped to real users.
Strong Python skills; comfort with TypeScript.
Hands‐on experience with at least one agent framework and multiple retrieval/context‐augmentation approaches.
Production experience with major LLM provider APIs from our Tech Stack.
Sound judgment on AI architecture choices.
Ability to select the right model and execution environment against cost, latency, accuracy, data‐residency constraints.
Knowledge of when traditional ML or no AI at all is right.
Ability to implement classical ML when fit.
Demonstrated experience measuring AI feature quality in production.
Metrics defined, test datasets built, regressions addressed.
Working professional English; strong async written communication for collaboration across Mexico, Europe, US time zones.
Strongly Preferred
Voice AI experience.
NEMT dispatch and customer‐service flows voice‐heavy, voice agents major product surface.
Regulated data experience HIPAA, PII/PHI handling.
Self‐hosting local‐self‐hosted LLM experience on‐prem or VPC.
Anthropic Claude API / Anthropic SDK experience, including Claude‐specific patterns.
Nice to Have
LLM observability / eval tooling experience.
Cost and latency optimization at LLM scale.
Traditional ML / data science background.
Django / PostgreSQL background.
Multi‐tenant SaaS experience.
Open‐source AI contributions or public agent projects.
#J-*****-Ljbffr

📌 Ai Application Engineer (Xico)
🏢 RouteGenie
📍 Xico