• Building and scaling agentic AI systems that autonomously execute complex, multi-step workflows end-to-end
• Designing AI orchestration layers, agent harnesses, tool calling frameworks, and execution pipelines for production LLM systems
• Developing and deploying LLM-powered infrastructure including retrieval pipelines, memory/context systems, evaluation layers, and workflow automation
• Building scalable backend services, APIs, and distributed event-driven architectures that support high-throughput AI workloads
• Creating production-grade AI systems focused on reliability, latency, observability, and iteration speed
• Designing integrations with external platforms, APIs, and third-party services to expand agent capabilities
• Improving AI system quality through evaluation frameworks, prompt iteration, retrieval optimization, and human-in-the-loop workflows
• Collaborating closely with product and engineering teams to rapidly prototype and ship new AI-native product experiences
• Evolving platform architecture to support rapid growth, increasing workflow complexity, and new AI capabilities over time

Do you have experience in Tooling?, * 4+ years of experience building and shipping production software systems, at least 2 years of AI engineering experience

• Strong backend engineering fundamentals with deep experience in Python
• Proven experience building AI-native products, agentic systems, LLM workflows, RAG pipelines, or orchestration infrastructure in production environments
• Strong understanding of distributed systems, async processing, event-driven architectures, and scalable backend design
• Experience working with modern AI tooling/frameworks such as LangGraph, LangChain, vector databases, workflow engines, or model serving infrastructure Ability to move quickly in ambiguous 0
• 1 startup environments with high ownership and autonomy
• Strong product instincts with an interest in building practical AI systems that solve real operational problems
• Comfortable operating across the stack when needed, including APIs, frontend integrations, internal tooling, and user-facing workflows
• Passion for AI infrastructure, automation, developer tooling, and the future of intelligent software systems

Pulled from the full job description

• Health insurance
• 401(k) matching
• Vision insurance
• 401(k) 3% Match
• Dental insurance
• Gym membership

We are looking for a Senior AI Engineer open to working 3-4 days/week in San Francisco or New York City.

Why join us?

• 401k with 3% company match
• Medical, dental and vision benefits
• Annual team offsites in cool places
• High impact, mission driven work
• You’ll be building systems that directly affect people’s lives and unlock opportunity for top global talent
• Proven traction and real scale ($10M ARR, profitable, and growing rapidly with a clear path to 5x revenue in 2026)
• $500 annual fitness stipend
• LLMs and agentic workflows are deeply embedded into the core product
• Engineering led culture
• Small, high caliber team with real ownership over product and technical decisions
• Zero to one through scale challenges
• You’ll work on everything from early architecture decisions to scaling systems for significant growth
• Already integrated into workflows of leading AI and technology companies
• Rapid iteration, frequent shipping, and direct user feedback loops

engineering #ai #llm #rag #llm-orchestration #ai-harness #tier1