Lead AI Engineer

Key Responsibilities

1. Agentic AI Architecture

• Design multi-agent orchestration flows for complex business workflows such as HR operations, sales support, proposal production, customer support, and executive operations.
• Build planner / deep-agent style systems that can break down goals, assign subtasks, use tools, verify outputs, and escalate to humans when needed.
• Define agent contracts, tool interfaces, memory strategy, state management, routing, retries, fallback behavior, and human-in-the-loop gates.
• Translate product goals into maintainable AI system architecture, not one-off demos

2. Engineering Leadership & Delivery

• Lead engineering execution from prototype to production deployment.
• Review architecture, code quality, reliability, security, and scalability of AI systems.
• Make build-vs-buy decisions for frameworks, model providers, vector stores, orchestration layers, evaluation tools, and observability stacks.
• Mentor engineers on agentic system design, testing, prompt/tool design, and production AI best practices.

3. Evaluation, Reliability & Observability

• Define measurable quality metrics for AI workflows: task success rate, tool-call accuracy, hallucination rate, escalation rate, latency, cost per task, and user satisfaction.
• Build evaluation harnesses for agent workflows, including test cases, regression checks, synthetic tasks, and real-work QA loops.
• Implement logs, traces, state inspection, error classification, cost monitoring, and alerting for AI operations.
• Design guardrails for privacy, access control, prompt injection, unsafe tool calls, and sensitive company data.

4. Cross-Functional AI Teamwork

• Work with Product, Design, HR, Sales, CS, and Management to map business workflows into agentic execution plans.
• Communicate technical trade-offs clearly to both executives and engineers.
• Help teams understand where AI should act autonomously, where it should assist, and where humans must stay in control.
• Create reusable playbooks and patterns so future AI teams can build faster.

5. Business Impact & Platform Thinking

• Tie engineering work to measurable outcomes such as reduced operation time, faster proposal cycles, higher HR response quality, lower support workload, or improved product retention.
• Design systems that can scale across multiple clients, departments, and use cases without rebuilding from scratch.
• Manage cost, latency, model selection, and operational risk as first-class product constraints. -
• Build platform components that become Jenosize's long-term competitive advantage.

Qualifications

• 3+ years of software engineering experience, with at least 2 years in AI/ML, LLM application development, automation platforms, or distributed systems.
• Strong backend engineering skills in TypeScript/Node.js, Python, or equivalent production stack.
• Hands-on experience building LLM applications with tool use, retrieval, function calling, workflow orchestration, or agent frameworks.
• Strong understanding of API design, queues/background jobs, database design, auth/access control, observability, and cloud deployment.
• Can design evaluation and monitoring for AI systems, not just rely on manual testing.
• Able to lead engineers, review architecture, and make decisions under ambiguity.
• Comfortable communicating with business leaders and non-technical stakeholders