Senior AI/ML Engineer

About the role

We're looking for a Senior AI/ML Engineer who will be working at the intersection of LLMs, real-time signal processing, and enterprise decision-making. This is not a research role or an isolated AI team position. You'll sit alongside domain engineers as you ship production AI systems to enterprise customers.

Responsibilities

• Signal detection and anomaly detection
• Statistical and ML-based detectors that identify meaningful patterns in portfolio signals — velocity changes, capacity saturation, dependency risks — from CDC event streams and external tool integrations.
• Insight synthesis engine
• An LLM-powered correlation engine that takes raw signals and produces actionable insights with root causes, confidence scores, and evidence chains.
• Planning Rules compiler
• A translation layer between natural language planning rules (written by portfolio managers) and the structured parameters that drive our Monte Carlo scheduling engine.
• Evaluation and testing frameworks
• The pipelines that ensure AI outputs are reliable, consistent, and improving over time.
• MCP tool definitions
• LLM-ready tool specs for domain capabilities (Item Store queries, capacity lookups, scenario simulations) that Tempo AI can discover and invoke at runtime within a hub-and-spoke MCP architecture already in production.

Requirements

Must Have:

• A track record of shipping LLM-powered features or products — prototypes don't count; we want to see things that real users have relied on.
• Hands-on experience orchestrating agents — multi-step reasoning, tool use, autonomous action with guardrails. Frameworks like LangChain, LlamaIndex, CrewAI, AutoGen, or equivalent (including rolling your own).
• Deep LLM engineering fundamentals: prompt engineering, RAG architectures, function calling / tool use, context management, evaluation-driven development.
• Production-quality engineering practices — you write code with tests, participate in code review, care about CI/CD and observability.
• Experience with event-driven or streaming data systems — CDC events, real-time pipelines, and the patterns that come with them.
• 5+ years in software engineering, with 3+ years focused on AI/ML in production systems.
• Ability to work embedded in a product team — collaborating daily with domain engineers, product managers, and designers, not just other AI specialists.
• Strongly Preferred:
• AWS Bedrock, Azure OpenAI, or GCP Vertex AI — we’re running on Bedrock with Claude today.
• MCP (Model Context Protocol) or similar tool-use / agentic frameworks.
• Anomaly detection, time-series analysis, or statistical signal processing.
• Building confidence scoring or calibration systems for AI outputs.
• A track record of absorbing work from external partners and making it your own — you know how to inherit an architecture, evaluate its decisions, and improve what you find.
• Proficiency in Kotlin or TypeScript alongside Python — our product platform is Kotlin/TypeScript; our AI platform is Python.

Qualifications

You build systems that run reliably in production, not notebook prototypes.

Skills

You use AI tools heavily in your own daily work — not as a novelty, but because they make you meaningfully more effective.

Benefits

• Impact: Work on meaningful products that empower enterprise users and improve productivity.
• Innovation: Be part of a culture that values creativity and innovation, with opportunities to make a real impact.
• Collaboration: Join a supportive, collaborative UX team that values openness, communication, and a continuous learning environment.
• Growth: Opportunities for professional development, including conferences, courses, and mentorship.

Pay

Competitive salary and benefits package.

Schedule

Full-time, remote-first work environment.