• Collaborate directly with the VP on prompt architecture, workflow design, and product roadmap. You’re a builder who shapes what gets built. • Own full-stack feature delivery from Postgres schema through API layer through React UI • Build and maintain multi-step AI pipelines: prompt chaining, structured output parsing, confidence scoring, failure recovery, and audit-trail logging • Integrate third-party financial data APIs into production tool workflows • Build financial document ingestion: parse uploaded spreadsheets and structured reports into typed data models for downstream AI processing • Maintain and extend the deterministic pre-processing and heuristic layers that make AI output reliable enough for audit • Contribute to the AI output evaluation framework: structured test inputs, expected outputs, scoring rubrics • Work cross-functionally with finance practitioners, product, design, and leadership to scope what gets built and push back on specs that miss

Role Description This is a remote role in the US and Canada. We are looking for a highly experienced Agentic AI Engineer with 7+ years of experience to design, build, and scale autonomous AI systems. This role focuses on developing advanced multi-agent systems capable of reasoning, planning, and executing complex workflows using LLMs. A key part of this role is implementing Spec-Driven Development (SDD), where structured specifications drive automated code generation, validation, and deployment workflows. You will lead the design of agent-driven platforms that automate SDLC, enterprise workflows, and decision systems. - Architect and build autonomous AI agents with advanced reasoning capabilities - Design multi-agent orchestration systems (planner, supervisor, executor) - Implement Spec-Driven Development (SDD) systems to convert requirements into executable workflows and code - Define and manage artifacts such as RequirementsPack, ArchitecturePack, and execution manifests - Design memory systems (vector DB, knowledge graph, hybrid RAG) - Optimize systems for scalability, latency, and cost - Integrate agents with enterprise platforms and APIs - Drive best practices in prompt engineering and context engineering - Mentor engineers and guide technical direction Qualifications - 7+ years of software engineering experience - 3+ years of experience with Generative AI / LLM systems - Strong programming skills in Python (preferred) or Go - Experience with distributed systems and backend architecture - Hands-on experience with cloud platforms (AWS preferred) - Proven experience designing scalable systems Requirements - LLM orchestration and reasoning systems - Prompt and context engineering - RAG and hybrid retrieval systems - Vector databases and semantic search - Agent frameworks (LangGraph, LangChain, or similar) - Multi-agent system design patterns - Spec-Driven Development (SDD) and spec-to-code workflows Preferred Qualifications - Experience building production-grade agent systems - Experience implementing SDD frameworks (OpenSpec, BMAD, or similar) - Familiarity with knowledge graphs and graph-based reasoning - Experience with Kubernetes, Docker, and scalable infrastructure - Experience with evaluation frameworks and guardrails Nice to Have - Experience with SDLC automation or coding agents - Familiarity with MCP or A2A communication patterns - Exposure to reinforcement learning or agent optimization - Experience in enterprise AI platforms What Success Looks Like - Deliver production-grade autonomous agents at scale - Successfully implement spec-to-code pipelines using SDD - Drive measurable impact through automation and AI - Improve system reliability, reasoning, and performance Benefits - Competitive Wages - Comprehensive Benefits package (medical, dental, vision, etc.) - Generous PTO to support work-life balance - 401K/RRSP Matching - Paid Parental Leave - Autonomy to grow and find your career path with supportive leadership - Remote working opportunities - Inclusive and diverse work environment

• Design and deliver production AI and agentic systems across document intelligence, workflow automation, and copilots • Own architecture decisions for LLM-based systems, including retrieval, orchestration, memory, tool use, and evaluation • Build and maintain evals and observability frameworks to ensure system quality, reliability, and performance • Optimize systems for cost and latency at production scale • Partner closely with AI Product to scope, sequence, and deliver high-impact features • Collaborate with Data Engineering on pipelines, schemas, and data quality foundations • Mentor engineers working on AI-adjacent systems and elevate team capabilities • Evaluate vendors, models, and tools through POCs, benchmarking, and cost-performance analysis • Ship quickly, iterate in production, and continuously improve system performance

• Design, build, and deploy production GenAI systems, including LLM applications, agentic workflows, RAG pipelines, and AI-powered search capabilities. • Architect scalable AI services using modern ML frameworks, model-serving tools, APIs, Docker, Kubernetes, and CI/CD pipelines. • Develop and optimize retrieval systems using embeddings, vector databases, semantic search, reranking, and structured data sources. • Fine-tune, adapt, and evaluate LLMs for domain-specific use cases using prompt engineering, supervised fine-tuning, LoRA / QLoRA, or related methods. • Build automated evaluation frameworks to measure model quality, prompt performance, retrieval accuracy, reasoning reliability, latency, and cost. • Implement observability for AI systems, including tracing, logging, performance monitoring, drift detection, and output-quality review. • Translate prototypes and research concepts into reliable product features that can scale in production. • Partner with product managers, data engineers, backend engineers, analysts, and business stakeholders to define AI capabilities and technical tradeoffs. • Review architecture, provide technical guidance, mentor junior team members, and promote strong engineering practices. • Create clear technical documentation, implementation plans, runbooks, and model lifecycle documentation.