Staff Software Engineer - AI Applied Engineering

At Quickbase, we help organizations build better ways to run their operations. Our products give teams the flexibility to create applications around how their work actually happens, connecting people, information, and processes so they can keep work moving as needs change. For more than 25 years, organizations have turned to Quickbase to solve operational challenges that off-the-shelf software wasn't built for. Today, we’re building on that foundation with new products and new possibilities for how people create, adapt, and improve the systems their work depends on. Working at Quickbase means helping find better ways forward. We’re a team of curious, collaborative people who care about solving problems, learning as we go, and building things that make work better for our customers and each other. Job Title: Staff Software Engineer, AI Applied Engineering Location: Sofia, Bulgaria Department: Engineering Reports to: Sr Manager, Software Engineering Job Summary We are building a new product at Quickbase that helps users in operations-heavy industries get their work done, with agents that do that work alongside them. The product runs on the agentic foundation built for Pave, our AI app builder, and what we are building on top of it is its own distinct product. As a Staff Software Engineer on the AI Applied Engineering team, you will work across the whole loop — shaping the idea, building the agents, shipping them to users, evaluating how they hold up with real work, and coming back to make them better. Job Duties and Responsibilities Build and ship fullstack features end to end, from design through production. Extend the Claude Agent SDK integration including MCP tool design, streaming (SSE) chat, context compaction, and tool-permission gating. Design and implement LLM-based features — RAG, agents, tool use — that power agents generating code, configuring workflows, and importing data. Build reliable AI pipelines with a focus on latency, cost, and failure modes. Define and implement evaluation strategies for AI outputs: offline (curated test sets, regression checks before shipping) and online (live production metrics including accuracy, override and escalation rates, latency, and cost). Own prompt and context engineering strategy and drive model and approach iteration. Design guardrails, tool-permission gating, and fallback mechanisms for non-deterministic outputs. Basic Qualifications Strong React and TypeScript experience with a track record of shipping production features. Comfortable working across frontend and backend. Hands-on experience with LLM applications including RAG, agents, and tool use, ideally with the Claude API, Agent SDK, or MCP tool servers specifically. Practical experience using LLMs in real production systems including streaming responses and prompt and context engineering. Demonstrated ability to move a feature from prototype to production including monitoring, cost control, and failure handling. Ability to reason about system design, not just models or prompts. A pragmatic engineering mindset — knows when not to use AI. Comfort working in a fast-moving, early-stage product environment. Strong architectural instincts with the ability to consider system and product impact when making decisions. Preferred Qualifications Experience with AI coding assistants such as Copilot, Cursor, Claude Code, or similar. Exposure to AWS-based backends including DynamoDB, Lambda, and ECS. Experience with search, recommendation systems, or other data-heavy systems. Experience with observability and monitoring of production systems. Familiarity with evaluating AI and ML features in production including offline eval sets, online metrics, and A/B testing. Exposure to durable or stateful execution engines such as Temporal or AWS Step Functions. Experience with vector databases. Production ML or MLOps experience. How We Think About AI At Quickbase, we view AI as a tool to accelerate how work gets done — not replace it. We encourage thoughtful use of AI to improve speed, quality, and decision-making, while maintaining strong judgment, accountability, and data integrity. Benefits Unlimited remote work policy 25 days of annual leave, 2 additional days off for volunteering Competitive remuneration package incl. an annual bonus Top-notch IT setup. Mental health support, life insurance, food vouchers Additional health insurance - for you and your loved ones Annual wellness support allowance External Professional Learning Opportunities Equal Opportunity Statement Quickbase is committed to building a diverse and inclusive workplace. We encourage candidates from all backgrounds to apply – even if you don’t meet every qualification listed. We are proud to be an equal opportunity employer.