Senior Software Engineer - Conversational AI (Python)

Team Vector builds the AI that talks directly to the customers of banks and credit unions. Our vision: To build the world's most intuitive and trusted customer-facing banking AI agents. Our mission: To build and scale a fully agentic voice AI framework that drives high-value customer interactions. Team Vector works across Europe and Vancouver, Canada. Tech stack: Python, Elixir, TypeScript, React (JavaScript); Amazon RDS for PostgreSQL, DynamoDB, S3; AWS; DataDog; Jenkins, Argo CD; Gemini, Claude Code; Terraform; Kafka, GitHub, Kubernetes, Docker. Hiring process involves an introduction, practical and team interviews, and a decision and offer.

Responsibilities

Design, build, and ship the core of the agentic voice AI framework, from conversation orchestration to tool calling and runtime architecture; Build and evolve harness controls (guardrails, grounding, policy checks, evaluation) that make LLM agents trustworthy for banking; Work on latency end to end: profile, measure, and optimize every stage of the real-time voice pipeline; Help unify runtime architecture and remove configuration friction so new banking use cases can launch quickly; Keep existing production systems stable and reliable while building what comes next; Work with product, design, and engineering teams across Europe and Vancouver to turn ambiguous problems into shipped outcomes; Use AI-assisted development tools daily and help set standards for reviewing and verifying agent-generated code

Requirements

AI Systems Experience: built production AI systems and understands LLM architecture (prompting and context management, tool use and agentic flows, retrieval and grounding, evaluation, tradeoffs between latency, cost, and quality); Architecture & Technical Judgment: owns design of complex components, makes sound tradeoffs, spots risk early; Excellent: Trusted, Fast Delivery: ships fast without cutting corners, track record of reliable outcomes, de-risking projects, owning quality including verifying agent-generated code; Applied AI Fluency: actively uses tools like Claude to design, build, review, and ship, can direct agents and verify their output; Proactive: sees problems early, partners with PMs from idea to delivery; Adaptable: thrives in a fast-paced environment with changing priorities and tools; Curious: quick learner who shares knowledge; Cross-Continental Collaboration: communicates clearly in writing and in person, works well on a distributed team, can overlap at least 2 hours a day with Pacific Time (9:00-11:00 AM PT); Leadership Instincts: sets direction, unblocks people, raises the bar without micromanaging

Nice to have

Real-time or voice AI experience; Experience with agent SDKs (such as the Claude Agent SDK or OpenAI Agents SDK); Prior tech lead, team lead, or mentorship experience