Software Engineer 2 - AI Platform

WEX•San Francisco, CA

1d•Remote

About The Position

We are seeking a seasoned Sr. Software Engineer in the North America Mobility organization. This role will sit in the Platform team that focuses on building AI Platform to support the feature development team to build robust features faster. You will contribute to the architecting and realization of our next-generation Agentic AI Platform. Within this capacity, you will be responsible for the design, development, and deployment of autonomous AI agents, skills, MCP servers, AI tools engineered for advanced reasoning, strategic planning, and the orchestration of intricate financial and operational workflows. Operating at the vanguard of generative AI, distributed systems, and fintech, you will empower WEX to deliver highly intelligent, proactive solutions to an expansive global user base. Our Platform team is dedicated to architecting scalable, robust, and maintainable UI and API platform solutions that empower internal feature development teams to build at velocity. Within the NAM Mobility ecosystem, our products facilitate strategic credit issuance to fleet organizations and their workforce through WEX-branded or co-branded credit instruments, accepted across a vast network of fueling stations and merchant partners. We provide fleet managers and operators with advanced spend orchestration capabilities, encompassing fuel discounts and sophisticated spend controls that permit precise configuration of merchant restrictions, transaction limits, and velocity thresholds to optimize operational efficiency.

Requirements

Bachelor’s degree in Computer Science or Software Engineering
2–5 years of professional experience in software engineering
Strong understanding of data structures and algorithms, object-oriented design, and problem-solving skills
Expertise in designing and developing internet-scale services with scalability, availability, security, and reliability design tenets
Excellent written and verbal communication skills, and a collaborative and empathetic mindset
Proficiency in backend development, with expertise in Java or C#, frameworks like SpringBoot, building and optimizing RESTful APIs, ODATA framework, and SQL
Hands-on experience building or contributing to AI/LLM-powered applications or agent-based systems
Familiarity with agent frameworks, tool-use patterns, and orchestration of LLM workflows
Experience integrating AI systems with external tools/APIs using MCP or similar protocols
Understanding of prompt engineering, embeddings, and vector-based retrieval systems
Experience designing systems for scaling AI workloads in production environments

Nice To Haves

Experience building AI skills & deploying AI solutions to production environments
Experience building production-grade AI agents or copilots
Familiarity with multi-agent systems and distributed AI architectures
Experience with vector databases (e.g., Pinecone, Weaviate, OpenSearch, Milvus)
Knowledge of AI evaluation techniques, safety practices, and responsible AI principles

Responsibilities

Design, develop, and maintain robust, scalable, and high-performance object oriented code in our backend services.
Develop public REST APIs using Java and internal gRPC APIs for inter-service and inter-system communication.
Craft systems designs, lead design decisions, and drive alignment with other senior engineers.
Write automated unit tests, integration tests, end-to-end tests, concurrency tests, load/performance tests.
Analyze existing systems to identify bottlenecks, tech debt, and implement scalability, and stability improvements.
Implement automation for testing, monitoring, healing, and scaling applications, continuous integration and deployment to reduce time to market.
Collaborate with cross-functional teams, including product managers, designers, and other engineers, to define and implement new features.
Conduct code reviews (comment, approve, seek revisions, merge), mentor junior and mid-level engineers, and actively promote engineering best practices.
Dive deep and troubleshoot complex issues, devise fixes, author root cause analysis documents, and ensure lasting performance and reliability.
Conduct objective and comparative analyses of competing technologies to advise the team of pros and cons of a technology solution.
Maintain robust documentation (design docs, run books, change management docs, and readiness plans).
Provide live-site support for production applications by monitoring systems, ensuring rapid incident resolution, and driving continuous improvement.
Drive cross-team projects as a single-threaded-owner (STO) or tech lead, and actively unblock other engineers to make progress.
Design and build agentic AI systems and services, enabling autonomous workflows, reasoning, and task execution within Mobility platforms.
Develop AI agents from scratch, including orchestration, tool usage, memory, and multi-step decision-making capabilities.
Implement and scale multi-agent architectures to support complex, distributed use cases across payments and fleet ecosystems.
Integrate systems using Model Context Protocol (MCP) or similar frameworks to enable secure and scalable interaction between AI agents, APIs, and enterprise data sources.
Build and optimize LLM-powered services (e.g., OpenAI APIs, LangChain) for production-grade performance, reliability, and cost efficiency.
Implement evaluation frameworks, observability, and guardrails to ensure correctness, safety, and compliance of AI-driven systems.
Design solutions for context management, memory, and retrieval-augmented generation (RAG) to enhance agent effectiveness.