Senior AI/ML Engineer

This is a fully remote position, open to applicants in United States.

📋 Description

• Detection of signals and anomalies

• Statistical and machine learning-based detectors that uncover significant patterns in portfolio signals — such as velocity changes, capacity saturation, and dependency risks — sourced from CDC event streams and external tool integrations. This goes beyond basic threshold alerts; it involves intelligent pattern recognition that differentiates between noise and genuine issues.

• Insight generation engine

• A correlation engine powered by LLM that transforms raw signals into actionable insights, complete with root causes, confidence scores, and evidence chains. It provides more than just “something is wrong” — it explains “why it’s wrong, what it indicates, and the recommended actions.”

• Compiler for planning rules

• A translation mechanism that bridges natural language planning rules (crafted by portfolio managers) and the structured parameters that direct our Monte Carlo scheduling engine. The LLM interprets intent, while the deterministic engine calculates schedules. You will design the communication between these two layers to ensure reliability.

• Frameworks for evaluation and testing

• The pipelines that guarantee AI outputs are dependable, consistent, and progressively improving. This includes regression suites for prompt modifications, A/B testing infrastructure for model updates, and confidence calibration — as vibes-based testing is insufficient at an enterprise level.

• Definitions for MCP tools

• LLM-ready tool specifications for domain functionalities (such as Item Store queries, capacity lookups, and scenario simulations) that Tempo AI can identify and utilize at runtime within a hub-and-spoke MCP architecture that is already operational.

⛳️ Requirements

• A proven history of delivering LLM-powered features or products — prototypes are not applicable; we seek evidence of solutions relied upon by actual users.

• Practical experience in orchestrating agents — involving multi-step reasoning, tool utilization, and autonomous actions with safety measures in place. Familiarity with frameworks like LangChain, LlamaIndex, CrewAI, AutoGen, or equivalent (including custom solutions) is essential.

• Strong foundational knowledge in LLM engineering: including prompt engineering, retrieval-augmented generation (RAG) architectures, function calling/tool utilization, context management, and evaluation-driven development.

• Adherence to production-quality engineering practices — you write code with tests, engage in code reviews, value CI/CD, and ensure observability. You build systems that function reliably in production environments, rather than mere notebook prototypes.

• Experience with event-driven or streaming data systems — including CDC events, real-time pipelines, and the associated patterns.

• At least 5 years of experience in software engineering, with a minimum of 3 years concentrated on AI/ML in production settings.

• Capability to work closely within a product team — collaborating daily with domain engineers, product managers, and designers, rather than solely with other AI specialists.

🏝️ Benefits

• A remote-first work environment

• Unlimited vacation in most of our locations!

• Comprehensive benefits including health, dental, vision, and savings plans.

• Additional perks such as training reimbursement, work-from-home reimbursement, and more.

• Diverse and dynamic teams engaged in challenging and exciting work.

• An opportunity to make a significant impact on our business.

• A wide variety of social activities (both in-person and virtual).

• Optional in-person meet-ups and opportunities to travel to our international offices.

• An employee referral program

• And so much more!