Titan is growing from a handful of live banking customers to thirty, then to hundreds. This role sits across the AI Toolbelt and Product Engineering lanes, owning the production AI systems that bank employees use every day — agent workflows, retrieval pipelines, and LLM integration layers. We bring a problem and expect a working solution.
Agent orchestration frameworks for multi-step reasoning, tool use, and constraint-based problem solving across banking workflows
RAG pipelines covering embedding generation, chunking, hybrid retrieval, and retrieval evaluation, calibrated for banking document types
LLM integration layers connecting banking models, APIs, and knowledge bases into reliable, auditable inference workflows
Evaluation infrastructure including behavioral contracts, regression baselines, and production observability for non-deterministic AI outputs
Backend services and APIs powering client-facing AI products at bank-tier uptime requirements
Qualifications
5+ years software engineering; 2+ years building and shipping production agentic AI or RAG systems
Agent framework experience: LangChain, LangGraph, PydanticAI, AutoGen, or Semantic Kernel
Background in software engineering with at least five years of experience, the last two spent building and operating production AI systems
Shipped agentic workflows, RAG pipelines, or LLM-powered applications to real users
Strong Python fundamentals across APIs and async systems
Fluent in LangChain, LangGraph, PydanticAI, or AutoGen
Hands-on experience with vector databases, retrieval evaluation, and observability tooling such as LangSmith, RAGAS, Arize, or Langfuse
Prior fintech or banking experience is a genuine advantage
Benefits
Competitive base and meaningful equity
Remote (US) with occasional travel to client sites and team offsites
What Success Looks Like
Within 90 days, ownership of at least one production AI workflow end to end with measurable improvements shipped to the retrieval or agent layer
Within six months, the go-to person on the team for hard agent and retrieval problems, operating independently from a high-level brief through to recommendation and implementation
At one year, a senior anchor on the AI engineering function with a track record of pulling others up and a credible path to leading other AI Engineers