MTS: AI Research Engineer

Type: Full Time, Hybrid Team: Research Focus: AI & Agent Systems Who We Are We're a team of founders, engineers, researchers, creatives, and operators building what we believe will be one of the defining companies of the AI era. Some of us came from startups. Some from academia. Some from hospitality, defense, design, or completely different worlds. We don’t care how you got here - we care about your energy, intelligence, curiosity, resilience, and ambition. Who We Are Not • We are not remote. We value the spontaneous moments that happen when we’re together - over dinner, in the hallway, around whiteboards. We like being around each other because the best conversations here rarely happen in meetings. • We are not your typical team. It’s not just the 10 countries we’re from, the languages we speak or our non-traditional backgrounds. We’re solving hard problems with people we respect - we make the most of our time together, we make it special. • We are not another “polished” SF startup . We value velocity over speed, raw talent over brands, and genuine human connection above all else. We value being successful, not looking successful. What You’ll Own & Build As a Member of Technical Staff within the Research Tribe, you’ll be one of the early engineers shaping the core systems that power Seldon. You won’t just build agents - you’ll design the infrastructure that governs how they operate: how they coordinate, how they’re evaluated, and how their behavior improves over time . This is a deeply technical role bridging distributed systems, machine intelligence, and product - turning stochastic models into reliable, production-grade systems. • Multi-Agent Systems Architecture: Design and implement agentic systems, rather than prompt chains, at scale. You’ll define agent topologies, robust orchestration layers, structured state management, persistent and scoped memory, tool-use registries and execution, and build structured, inspectable systems. You’re building a long-running harness-based agentic platform, not wiring together LLM API calls. • Behavioral & Persona Modeling: Simulate user archetypes with goal-directed behavior. You’ll design data-grounded personas, enable “computer-use” on real interfaces, and develop agents with critique and reflection loops. You’re producing measurable, actionable behavior. • Evaluation & Prompt Engineering: Design prompt schemas and reasoning templates as integrated systems. You’ll build frameworks that measure behavioral fidelity and failure modes, and implement automated and HITL feedback. If it can’t be measured, it doesn’t ship. • Signal & Insight Systems: Build systems that transform raw agent outputs into high-signal insights. You’ll cluster observations across runs, implement severity scoring, and map behavioral signals to product decisions. Turn noisy outputs into decisions. • Production Reliability: Build the infrastructure to operate agents in production. You’ll implement tracing, attribution, and cost monitoring, detect failure modes and design fallbacks, circuit breakers, and evaluation pipelines. The bar is production reliability. Who You Are • Systems, Not Prompts: You prioritize state machines, orchestration layers, and tool-use contracts over prompt hacking. You build for reliability, inspectability, and improvability - you’re uncomfortable with “it just works sometimes.” If it can’t be measured, it doesn’t ship. • Production Experience: You have 5+ years building complex software and 2+ years shipping agentic LLM systems. You’ve built harnesses where agents manage tool selection, error recovery, and multi-step execution autonomously in production environments that run, break, and evolve. • Orchestration Systems: You’re experienced with multi-agent orchestration, sandboxed e