Senior AI/ML Engineer

Tempo

38d•Remote

About The Position

Tempo is seeking a Senior AI/ML Engineer to work at the intersection of LLMs, real-time signal processing, and enterprise decision-making. This role involves shipping production AI systems to enterprise customers, working alongside domain engineers. The ideal candidate will have extensive experience with LLMs and autonomous agents, strong opinions on AI product engineering, and a proactive approach to problem-solving using agent pipelines. Initially, you will collaborate with external AI partners to integrate their work and establish best practices for the broader engineering team. Over time, you will become the internal expert for AI engineering, guiding decisions on prompt design, evaluation strategy, model selection, and agent architecture.

Requirements

A track record of shipping LLM-powered features or products to real users.
Hands-on experience orchestrating agents, including multi-step reasoning, tool use, and autonomous action with guardrails, using frameworks like LangChain, LlamaIndex, CrewAI, AutoGen, or equivalent.
Deep LLM engineering fundamentals: prompt engineering, RAG architectures, function calling / tool use, context management, evaluation-driven development.
Production-quality engineering practices: writing code with tests, participating in code review, CI/CD, and observability.
Experience with event-driven or streaming data systems, including CDC events and real-time pipelines.
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.

Nice To Haves

Experience with AWS Bedrock, Azure OpenAI, or GCP Vertex AI.
Familiarity with MCP (Model Context Protocol) or similar tool-use / agentic frameworks.
Experience with anomaly detection, time-series analysis, or statistical signal processing.
Experience building confidence scoring or calibration systems for AI outputs.
A track record of absorbing work from external partners and improving inherited architectures.
Proficiency in Kotlin or TypeScript alongside Python.

Responsibilities

Signal detection and anomaly detection using statistical and ML-based detectors to identify meaningful patterns in portfolio signals from event streams and external integrations.
Developing an LLM-powered insight synthesis engine to correlate raw signals and produce actionable insights with root causes, confidence scores, and evidence chains.
Designing a translation layer between natural language planning rules and the structured parameters for a Monte Carlo scheduling engine, ensuring reliable communication between LLM intent interpretation and deterministic engine computation.
Building evaluation and testing frameworks, including regression suites for prompt changes and A/B testing infrastructure for model updates, to ensure AI outputs are reliable, consistent, and improving.
Creating LLM-ready tool specifications for domain capabilities within a hub-and-spoke MCP architecture.