About the role
Join Optibus' GenAI team to build and extend the AI assistant embedded across our product suite. The platform is a production LLM agent system that's integrated into multiple host applications, backed by a RAG knowledge base and an evaluation-driven development workflow.
You'll work end-to-end: agent design, tool implementation, retrieval quality, integration into existing product UIs, cloud infrastructure, and evaluation/observability. The platform already ships to customers — you'll extend it, raise its quality bar, and help define where it goes next.
What you'll do
- Design and evolve agents - build LLM agents with tool use, routing, and human-in-the-loop flows.
- Implement tools and integrations - expose product capabilities to the agent, with multi-tenant context, via internal APIs and MCP servers.
- Own retrieval quality - contribute to our RAG pipeline end-to-end: ingestion, embeddings, vector search, and reranking.
- Define and evolve host integration contracts - collaborate with host application teams to integrate the assistant into product UIs built on different frontend stacks. You own the shared remote module and the integration API; host teams own their stacks.
- Drive evaluation-led development - write evaluators (rule-based, LLM-as-judge, multi-turn), maintain CI eval gates, and use traces and feedback to debug production behavior.
- Operate the platform - own deployments, observability, and the performance and cost of LLM-backed services.
- Establish engineering practices** for AI-specific work: prompt versioning, eval coverage, testing, and code review.
- 5+ years of professional software engineering experience.
- Strong TypeScript — the primary language across our backend, frontend, and agent code.
- Production experience with LLM-based applications, including prompt engineering, agent/tool-calling design, and RAG.
- Hands-on experience with an agent framework (e.g., LangGraph, LangChain).
- Vector databases and semantic search with embedding-based retrieval.
- Cloud experience on AWS — compute, storage, IAM, and managed LLM services (e.g., Bedrock or equivalent).
- Solid web fundamentals — REST APIs, WebSockets, auth (token/OIDC), and modern React.
- Docker and standard CI/CD practices.
Strongly preferred
- Python for data and ingestion pipelines.
- MCP (Model Context Protocol) — building servers, clients, or tooling.
- LLM observability and evaluation platforms (e.g., LangSmith).
- Module Federation or other micro-frontend integration patterns.
- Experience designing APIs or SDKs consumed by multiple client teams across different tech stacks.
- Infrastructure as code (AWS CDK and/or Pulumi).
- B2B SaaS background with multi-tenant context.
- Interest in the public-transit domain.
About Optibus:
Optibus is a unified software platform revolutionizing public transportation planning, scheduling, and operations in over 8,000 cities worldwide. Using AI, ML, and optimization algorithms, it empowers agencies to design more efficient, equitable, and sustainable transit networks, enhancing passenger access, reducing emissions, and improving driver conditions. With offices globally and a team of 350+ employees, Optibus fosters a collaborative culture centered on innovation, determination, and impact. As the first unicorn in public transportation technology, Optibus is driving the modernization of mass transit to make it the preferred choice for cities and passengers alike.
Why Join Optibus?
- Be part of a company revolutionizing public transportation with cutting-edge technology.
- Collaborate with global teams passionate about sustainability and innovation.
- Enjoy a dynamic and inclusive workplace culture that values growth and creativity.
- We offer a hybrid work environment, with employees expected to be in the office 3 days a week. The remaining days can be worked remotely to support work-life balance and flexibility.
Optibus is proud to be an equal opportunity employer. We hire talented individuals, regardless of gender, race, ethnicity, ancestry, age, disability, sexual orientation, gender identity or expression, cultural background, religious beliefs, or any other characteristic protected by federal, state, or local laws. It is our responsibility at Optibus to provide an inclusive and accessible interview experience for all. We will provide reasonable accommodations for all candidates in need of individualised support during the hiring process.
Skills Required
- 5+ years of software development experience across multiple technology stacks
- Strong Python programming skills
- Proficiency in TypeScript for frontend integration of AI features
- Proven experience developing and deploying generative AI applications in production environments
- Hands-on experience with large language models (LLMs), fine-tuning, and prompt engineering
- Knowledge of microservice architecture and cloud-based deployment
- Experience with containerization (Docker), orchestration (Kubernetes), and CI/CD pipelines
- Strong understanding of RESTful APIs and modern web development practices
- Solid software engineering fundamentals including version control, testing, and code review
What We Do
Optibus’ vision is to be the modern operating system for mass transportation. Optibus is an end-to-end, cross-functional software platform for transportation planning, scheduling, rostering, and operations. Founded in 2014, transportation agencies and operators in over 5,000 cities worldwide trust Optibus to increase efficiency and ridership, improve service quality, promote transportation equity, reduce emissions and costs, and modernize their operations. Our platform enables operators and agencies to plan and analyze better routes, schedules, rosters, and much more. Optibus is a cloud-native solution powered by artificial intelligence (AI) and advanced optimization algorithms that are revolutionizing the transportation industry across the globe. Optibus has been recognized as a technology pioneer by the World Economic Forum for its role in transforming the transportation industry, promoting equity, sustainability, and smart cities.









