[Remote] Senior AI/ML Engineer

Note: The job is a remote job and is open to candidates in USA. Tempo Software is seeking a Senior AI/ML Engineer to build and ship production AI systems for enterprise customers. The role focuses on signal and anomaly detection, LLM-powered insight synthesis, translating planning rules for scheduling systems, and establishing evaluation frameworks and agent tools.

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. Not simple threshold alerts; intelligent pattern recognition that knows the difference between noise and a real problem
• Insight synthesis engine An LLM-powered correlation engine that takes raw signals and produces actionable insights with root causes, confidence scores, and evidence chains. Not just “something is wrong” — but “why it’s wrong, what it means, and what you should do about it.”
• 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. The LLM interprets intent; the deterministic engine computes schedules. You’ll design how these two layers communicate reliably
• Evaluation and testing frameworks The pipelines that ensure AI outputs are reliable, consistent, and improving over time. Regression suites for prompt changes, A/B testing infrastructure for model updates, confidence calibration — because vibes-based testing doesn’t scale at enterprise scale
• 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

Skills

• 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. You build systems that run reliably in production, not notebook prototypes
• 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
• 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. You'll work across both
• You use AI tools heavily in your own daily work — not as a novelty, but because they make you meaningfully more effective
• You have strong opinions (loosely held) about what makes AI products trustworthy versus impressive-but-fragile
• You're energized by a space that's moving fast, and you track model releases, emerging agent frameworks, and new patterns as they happen
• You're as comfortable writing an Architecture Decision Record as you are writing a prompt
• Monte Carlo simulation, optimization algorithms, or scheduling systems
• Background in portfolio management, project management, or resource planning
• Experience in enterprise SaaS — multi-tenancy, compliance, audit trails
• Contributions to open-source AI/ML projects

Benefits

• Opportunities for professional development, including conferences, courses, and mentorship.
• Remote First work environment.
• Unlimited vacation in most of our locations.
• Health, dental, and vision benefits, and a savings plan.
• Training reimbursement.
• WFH reimbursement.
• Social activities (both in person and virtual).
• Optional in-person meet-ups.
• Ability to travel to international offices.
• Employee referral program.

Company Overview

Company H1B Sponsorship