Senior AI/ML Engineer in Pittsburgh

AI focus: LLMs, agent orchestration, RAG architectures, evaluation pipelines (Claude/Bedrock integration), You will design, build, and operate the AI components that make our platform intelligent and trustworthy:

• Signal & anomaly detection - Build statistical and ML detectors that separate noise from real problems in CDC event streams and external integrations.
• Insight synthesis engine - Ship an LLM-powered correlation engine that returns root causes, confidence scores, and evidence chains, not just alerts.
• Planning rules compiler - Translate natural- planning rules into structured parameters for a deterministic Monte Carlo scheduling engine.
• Evaluation & testing frameworks - Create regression suites, A/B testing, and confidence-calibration pipelines so model changes are safe and measurable.
• MCP tool definitions - Define LLM-ready tool specs (Item Store queries, capacity lookups, scenario simulations) for runtime tool use in a hub-and-spoke agent architecture.

• Proven track record shipping LLM-powered features or products (not prototypes) that real users rely on.
• Hands-on experience orchestrating agents (multi-step reasoning, tool use, autonomous action with guardrails) - LangChain, LlamaIndex, AutoGen, CrewAI, or equivalent.
• Deep LLM engineering fundamentals: prompt design, RAG architectures, function-calling/tool use, context management, and evaluation-driven development.
• Production engineering discipline: tests, CI/CD, observability, and reliability for production AI systems.
• Experience with event-driven or streaming systems (CDC, real-time pipelines).
• 5+ years software engineering, with 3+ years focused on AI/ML in production.
• Comfortable working embedded in a product team - collaborating daily with domain engineers, product managers, and designers.

experience

• Experience with AWS Bedrock, Azure OpenAI, or GCP Vertex AI (we run on Bedrock with Claude today).
• Familiarity with MCP (Model Context Protocol) or similar agentic frameworks.
• Background in anomaly detection, time-series analysis, or statistical signal processing.
• Experience building confidence scoring / calibration systems for AI outputs.
• Proficiency in Kotlin or TypeScript in addition to Python (our product platform is Kotlin/TypeScript; AI platform is Python).
• History of absorbing work from external partners and improving inherited architectures.

Nice to have

• Monte Carlo simulation, optimization, or scheduling systems.
• Domain experience in portfolio, project, or resource planning.
• Enterprise SaaS experience (multi-tenancy, compliance, audit trails).
• Open-source contributions to AI/ML tooling or frameworks.

$220000 - $300000 USD per year

Founded in 2006, we’re one of the largest app vendors (300+ employees) supporting 30,000+ customers worldwide - including Amazon, Disney, Dell, PayPal, and Hulu. In fact, one in three Fortune 500 companies relies on our products!!