What You’ll Do
Architect the framework: Design, build, and ship the core of our agentic voice AI framework, from conversation orchestration to tool calling and runtime architecture.
Build the model harness: Because banking is highly regulated, every response must be safe, compliant, and on-brand. You will build and evolve the strict controls—guardrails, grounding, policy enforcement, and verification layers—that make our LLM agents trustworthy.
Optimize latency end-to-end: People notice every pause in a conversation, making latency a first-class engineering constraint. You will profile, measure, and shave milliseconds off every hop across speech recognition, LLM inference, tool calls, and speech synthesis.
Streamline & stabilize: Help unify our runtime architecture and remove configuration friction so new banking use cases can launch quickly, all while keeping existing production systems perfectly stable.
Shape AI-assisted engineering: Use AI-assisted development tools daily and help set the standards for how we review and verify agent-generated code.
Our Collaboration Model
Team Vector operates across Europe and Vancouver, Canada. While we are remote-first, we have physical offices in both Tallinn and Tartu, so you’ll have the option to work from there if you prefer. To collaborate closely with the Vancouver team, you are expected to overlap at least 2 hours daily with Pacific Time (9:00–11:00 AM PT), making your typical working hours approximately 13:00 – 21:00 EET. The full team gathers in Estonia twice a year to innovate and connect in person.
What We’re Looking For
We’re looking for a Senior Software Engineer. While our core needs involve Python, Elixir and Ruby, we strongly value architectural thinking with drive and ability to learn fast over language loyalty. What is even more important is architecture and AI fluency. You should be prepared to work across different stacks, selecting and mastering the best tool for the challenge at hand.
AI Systems Experience: You have built production AI systems and deeply understand LLM architecture (prompting, agentic flows, grounding, and latency/cost tradeoffs). Real-time voice AI and agent SDK experience (Claude Agent SDK or OpenAI Agents SDK) are a strong plus.
Architecture & Technical Judgment: You own the design of complex components, make sound tradeoffs, and spot risks early—system design is a highly valued skill as AI writes more code.
Trusted, Fast Delivery: You ship quickly and reliably without cutting corners, taking full ownership of quality for both human- and agent-generated code.
Applied AI Fluency: You actively use AI tools like Claude to design, build, and review code, knowing exactly how to direct agents and verify their output.
Proactive & Adaptable: You thrive as the AI landscape rapidly changes, partnering with PMs to drive projects from idea to delivery while spotting and solving problems before being asked.
Curious & Collaborative Leader: You tackle unfamiliar problems head-on, learn rapidly, and share knowledge. You set direction and unblock teammates (prior tech lead or mentorship experience is a plus).
OUR TECH STACK
Coding languages: Python, Elixir, TypeScript, React (JavaScript)
Persistence: Amazon RDS for PostgreSQL, DynamoDB, S3
Infrastructure: AWS
Monitoring: DataDog
CI/CD: Jenkins, Argo CD
AI: Gemini, Claude Code
Infrastructure as Code: Terraform
Other: Kafka, GitHub, Kubernetes, Docker
Glia is an equal-opportunity employer. Glia does not discriminate against any employee or applicant because of race, creed, color, religion, gender, sexual orientation, gender identity/expression, national origin, disability, age, genetic information, veteran status, marital status, pregnancy or related condition (including breastfeeding), or any other basis protected by law.
The Glia Talent Acquisition team uses @glia.com http://glia.com and @ darina.danchenko@gliatalent.comgliatalent.com http://gliatalent.com email addresses for coordinating interviews, providing updates, and sending documents.
Our hiring process involves an introduction, practical and team interviews, and a decision and offer. For more information, visit our Recruitment Privacy Notice page https://www.glia.com/eu-recruitment-privacy-notice or contact our talent team via talent@glia.com