Senior AI Engineer
Posted 1ds ago
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
Senior AI Engineer building reliable, observable agentic systems for STARLIMS laboratory software. Developing runtimes, production agents, evaluation harnesses, safeguards, and enterprise integrations.
Responsibilities:
- Design and build the runtime for agent planning, execution loops, tool calling, state management, durable execution, and failure recovery
- Build safe access layers for platform data and external systems
- Design agent and workflow coordination, delegation, and handoffs
- Make agent behavior versionable, testable, measurable, and regression-safe
- Build reusable primitives for configuring new agents
- Convert domain workflows into working agents with defined goals, actions, execution flows, failure handling, and success criteria
- Ground agent decisions and outputs in authoritative enterprise data
- Implement human-in-the-loop approval gates, override capture, uncertainty handling, and evidence for decisions
- Use user corrections and overrides to improve agents
- Build evaluation harnesses for multi-step behavior and define production quality, reliability, latency, cost, and intervention metrics
- Implement guardrails, fallbacks, timeouts, cost ceilings, observability, and tracing
- Design safeguards against prompt injection, unsafe tool use, excessive permissions, data leakage, and other agent security risks
- Manage prompt evolution, model drift, and non-determinism across releases
- Integrate agents with platform APIs and third-party enterprise systems
- Build retrieval and context pipelines for reliable, permission-aware enterprise data
- Design controlled automated execution paths with traceable audit trails
- Build and operate AWS backend services
- Own significant system architecture and contribute to technical decisions
- Contribute to infrastructure-as-code and deployment pipelines
Requirements:
- 6+ years of software engineering experience, including production systems
- Experience building production LLM systems with tool-using or multi-step agentic workflows
- Strong understanding of LLM behavior, limitations, and failure modes
- Experience with LLM APIs, tool and function calling, and planning and execution loops
- Experience evaluating and debugging non-deterministic systems
- Solid backend and cloud experience with AWS or equivalent
- Proficiency in TypeScript and/or Python
- Comfortable debugging distributed and non-deterministic systems
- Comfortable trading off accuracy, latency, reliability, and cost
- Comfortable working in ambiguous problem spaces
- Comfortable owning production systems end-to-end
- Comfortable choosing conventional software when AI is not appropriate
- Nice to have: C# and Microsoft .NET Framework
- Nice to have: MCP and related agent/tool protocols
- Nice to have: agentic evaluation pipelines and metrics
- Nice to have: regulated or domain-heavy systems experience
- Nice to have: retrieval and grounding techniques
- Nice to have: workflow and durable-execution platforms such as Temporal, Step Functions, or n8n
- Nice to have: containerization and orchestration with ECS, EKS, or Kubernetes
- Nice to have: infrastructure as code with Terraform or similar



















