• Support the design and build of a OneStream platform solution under the guidance of a Technical Lead • Develop and configure: • Data integrations • Cubes and dimension metadata • Workflows and dashboards • Business rules and financial calculations • Participate in client discovery sessions to gather and refine business requirements • Demonstrate system functionality and capabilities to stakeholders • Contribute to: • System testing documentation and execution • User acceptance testing (UAT) • End-user training materials and delivery • Collaborate with functional and technical teams to ensure alignment with financial reporting requirements

• You will join as a Senior Developer/Lead and manage demanding client projects. • You will become familiar with our tech stack and existing clients. • You will take on leadership of the small development team. • You will coordinate freelancers and optimize processes.

Role Description Biggy Engineering is building BigPanda’s generative AI platform for IT Operations: AI-powered incident response, prevention, automation, knowledge retrieval, workflow execution, and operational intelligence. We are expanding what enterprise IT teams can do with AI, not just making existing workflows slightly faster. This is an early-stage product environment inside an established enterprise company. We move quickly, work directly with customers, make pragmatic tradeoffs, and prioritize shipping differentiated customer value over perfect process. Engineers on this team are expected to operate with extreme ownership, high urgency, and a strong bias for action. The ideal candidate is a strong product-minded software engineer with hands-on AI experience, not a research-first ML profile. We care most about agency, judgment, output, speed, customer empathy, technical depth, and the ability to turn ambiguity into working software. This role is informed by the Biggy engineering scope already demonstrated across full-stack systems, APIs, workflow orchestration, secure ingestion, vector database indexing, automation frameworks, agent workflows, and direct customer collaboration. Responsibilities - Build production-grade software across backend services, APIs, web applications, workflow systems, AI agents, enterprise integrations, and automation platforms. - Architect and implement AI-native capabilities using LLMs, prompting, tool calling, agent orchestration, RAG, vector search, knowledge graphs, embeddings, and structured/unstructured enterprise data. - Use AI coding platforms such as Cursor, Claude Code, and similar tools as a core part of your development workflow to increase speed, exploration, and delivery quality. - Write high-quality prompts for development, debugging, product behavior, agent execution, data extraction, reasoning workflows, and customer-facing AI experiences. - Own features from concept through delivery, including customer discovery, technical design, implementation, manual validation, release, bug resolution, and iteration. - Work directly with customers, GTM, product, and other engineers to identify high-value problems and translate them into product capabilities. - Make pragmatic tradeoffs between speed, quality, reliability, cost, latency, scalability, and customer impact. - Move fast in ambiguous problem spaces without hiding behind process, excessive documentation, or prolonged design debates. - Manually validate AI and product behavior with care, especially where automated tests and evals are insufficient for probabilistic systems. - Respond rapidly and transparently to bugs, regressions, and customer-impacting issues. - Collaborate through paired development, design discussion, code review, debugging, and direct technical debate. - Help raise the team’s bar for velocity, technical judgment, ownership, and customer-focused execution. Qualifications - Strong software engineering fundamentals across backend, full-stack, distributed systems, APIs, or product engineering. - Hands-on experience building AI-enabled product capabilities with LLMs, RAG, vector databases, embeddings, agents, workflow automation, knowledge systems, or related technologies. - Strong practical prompting skills, including prompt iteration, context design, tool-use instructions, structured outputs, and failure-mode analysis. - High proficiency with modern AI development tools such as Cursor, Claude Code, ChatGPT, or similar platforms. - Ability to architect and build agent systems that can reason, retrieve context, call tools, execute actions, handle errors, and operate safely in enterprise environments. - High agency: you learn what you need to learn quickly, make forward progress independently, and do not wait for someone else to define every step. - Extreme ownership: you care about outcomes, customer impact, reliability, and follow-through, not just completing assigned tickets. - High velocity: you are motivated to ship, learn, and iterate quickly while maintaining sound engineering judgment. - Customer curiosity: you want direct exposure to users and are comfortable using customer feedback to shape priorities. - Product judgment: you can distinguish between what is technically interesting and what creates meaningful customer value. - Healthy conflict: you can challenge weak ideas directly while remaining considerate, collaborative, and low-ego. - Comfort with uncertainty, changing priorities, incomplete requirements, and fast iteration cycles. - Excitement about applying AI to real enterprise IT Operations problems, not just building demos. Technical Areas You May Work In - TypeScript / Node.js backend services - Fastify or similar API frameworks - React / Next.js customer-facing applications - Slack and Microsoft Teams applications - Agent workflow engines and action execution systems - RAG pipelines, vector databases, embeddings, and retrieval systems - Knowledge graphs and enterprise knowledge modeling - Prompt engineering, context engineering, and tool-use design - ServiceNow, ITSM, monitoring, alerting, and incident management integrations - Data ingestion, indexing, synchronization, and unstructured data processing - S3, SQS, Lambda, and AWS-based service architecture - Authentication, authorization, OAuth, SSO, API keys, and RBAC - Incident response, change risk, and incident prevention use cases (domain knowledge/awareness) Benefits - Competitive equity - Remote-first environment - Unlimited PTO - Twelve (12) paid holidays throughout the year - Comprehensive health benefits - #PandaParent support: Financial assistance for fertility, adoption, and surrogacy expenses, plus up to eighteen (18) weeks of fully paid leave for birthing parents and up to twelve (12) weeks for non-birthing parents. - Financial planning services - Employee learning & development budget - Values-based recognition (quarterly and annually) - Social community & ERG programs - Dog friendly office - Lunches provided in office - Flexible work environment along with a work-from-home stipend to support remote work arrangements - Values-based culture

• You will play a key role in the AI/ML strategy for the Operations area, collaborating to help the team fulfill its role as owner of the company's Revenue Strategy. • Your work will be to develop robust, scalable solutions that enable Marketing, Sales, and Customer Success operations to become more data-driven, increasing efficiency and impact on business results. • Build training pipelines for Machine Learning and Deep Learning models (supervised, unsupervised, and language models - LLMs) to solve high-impact problems. • Implement and maintain robust MLOps pipelines (CI/CD, versioning, model drift and data drift monitoring) to automate the full model lifecycle. • Integrate AI models with front-end, back-end, and operational systems, ensuring high availability, low latency, and scalability. • Work collaboratively with Data Engineers to ensure the supply of high-quality features and optimized infrastructure for training and inference. • Monitor model performance in production, ensuring performance and retraining when necessary, and propose innovative architectural solutions in MLOps and AI.