Role Description IDC is building the next generation of AI-powered intelligence platforms that transform how technology decisions get made. We are looking for a Senior AI/Agent Engineer to serve as the player-coach dev lead for the new Memory / Living Intel Pod. - Lead a cross-functional pod of 4-8 engineers spanning AI/LLM and backend infrastructure disciplines. - Set the technical direction for the pod's memory and proactive intelligence systems. - Build memory capabilities that give the platform persistent, cross-session understanding of each user. - Design proactive intelligence systems that monitor artifacts for changes, summarize what matters, and route alerts to the right channel. - Integrate with the AI agent pipeline and channel adapters built by adjacent teams. - Define interfaces and contracts with adjacent teams. - Write production code. This role involves coding more than 50% of the time. Qualifications - 7+ years of professional Python development experience. - Proven experience building LLM-powered systems in production environments. - Player-coach track record leading teams of 4-8 engineers while remaining a significant code contributor. - Experience leading across disciplines, bridging AI/LLM engineering and infrastructure engineering. - Strong background in asynchronous system design: background jobs, event-driven patterns, scheduled processing. - Quality-minded approach to system design and code. - Comfort with ambiguity and building from scratch. Requirements - Experience building systems that maintain or evolve user context and state over time. - Familiarity with semantic search, embeddings, and vector databases (e.g., Snowflake Cortex, Pinecone, Weaviate). - Background in event-driven architectures, job scheduling, and change detection patterns. - Experience with LLM observability tools (e.g., Langfuse, LangSmith, Weights & Biases). - Track record of standing up new teams from zero. Benefits - 15 vacation days per year (increases with tenure; carryover allowed). - 10 paid sick days per year. - 1 week paid new parenting leave. - Flexible work options (remote, part-time, flexible hours). - Health, dental, vision, and paramedical coverage for you and your family. - $1,600 annual healthcare spending account. - Employee Assistance Program for counseling and support. - Best Doctors medical second opinions. - Life, AD&D, and long-term disability insurance. - Retirement savings plan with company match (up to 4% of salary). - $75/month technology allowance for home office or phone expenses. - Company-paid cell phone plan.

• Own the end-to-end technical direction and architectural patterns for high-impact GenAI initiatives. • Establish and evolve the CI/CD and automated evaluation pipelines. • Lead the evaluation and prototyping of cutting-edge techniques to make high-stakes decisions for our AI roadmap. • Implement sophisticated observability hooks and monitoring strategies to trace agent logic and optimize performance. • Drive the experimentation loops to ensure solutions are both cutting-edge and commercially viable. • Act as the principal design authority and code reviewer, mentoring engineers and championing practices.

• Own the end-to-end technical direction and architectural patterns for high-impact GenAI initiatives • Establish and evolve the CI/CD and automated evaluation pipelines for non-deterministic AI outputs • Lead the evaluation and prototyping of cutting-edge techniques for AI roadmap decisions • Implement sophisticated observability hooks and monitoring strategies to trace agent logic • Drive the experimentation loops required to hit aggressive accuracy, latency, and cost targets • Act as the principal design authority and code reviewer for the team, mentoring engineers and championing secure-by-design practices

• Architect and code sophisticated AI modules, including high-performance embedding pipelines, custom chunkers, and advanced retrieval evaluators • Lead the integration of intelligent agent services with diverse internal and external APIs and vector databases • Stay at the bleeding edge of AI research, implementing the latest advancements in fine-tuning, RLHF, and prompt engineering frameworks • Drive agile excellence by spearheading sprint deliveries and collaborating with cross-functional leaders • Champion code quality and team growth by performing high-level peer reviews • Architect and implement modular, cloud-native microservices that integrate GenAI into our production ecosystem • Take ownership of the production lifecycle by building robust CI/CD pipelines • Drive technical excellence by developing comprehensive evaluation suites