Senior AI Engineer

We are building production-grade AI systems that transform complex scientific and regulatory content into structured, machine-readable knowledge. Our platform combines large language models, agent-based architectures, deterministic business logic, validation frameworks, and scalable software services to automate workflows that traditionally require significant human expertise. We are seeking a Senior AI Engineer to contribute directly to the MethodConnect codebase and work on responsibilities similar to those currently led by AI engineering. This is a hands-on software engineering role focused on designing, implementing, refactoring, and operating reliable AI-powered capabilities. The ideal candidate can move beyond prototypes and prompt experimentation. They can analyze complex processing behavior, identify reusable patterns, translate domain requirements into clear system rules, and implement maintainable production code.

Required Experience:

• 5+ years of professional software engineering experience, including substantial hands-on development in Python.
• Practical experience developing applications with LLMs, NLP, machine learning, or other AI capabilities.
• Strong software design skills, including modular architecture, reusable components, design patterns, and maintainable code.
• Experience with automated testing, code review, version control, and CI/CD practices.
• Strong debugging and root-cause analysis skills across code, data, and distributed workflows.
• Experience building agentic AI systems or multi-step LLM workflows using LangGraph, LangChain, Semantic Kernel, or comparable frameworks.
• Experience building and maintaining production backend services, APIs, or data-processing systems.
• Experience with structured-output generation, tool calling, prompt orchestration, state management, and model fallback strategies.
• Experience working with structured and semi-structured formats such as JSON and XML, including schema validation and transformation.
• Experience with AWS services, containerized applications, infrastructure as code, and production observability.
• Familiarity with LLM evaluation, golden datasets, regression testing, and quality measurement.
• Domain experience in pharmaceutical, healthcare, laboratory, scientific, regulatory, or other quality-sensitive environments.

Responsibilities:

• Design, build, and enhance AI agents and workflows that convert complex scientific content into structured, machine-readable outputs.
• Contribute production-quality Python code directly to the MethodConnect codebase, including new capabilities, refactoring, and defect resolution.
• Analyze instruction patterns, edge cases, and ambiguous requirements before implementation, then translate findings into clear processing rules.
• Build reliable services and pipelines with schema validation, error handling, logging, traceability, testing, and observability.
• Investigate failures across prompts, data, orchestration, and application logic, and implement durable root-cause fixes.
• Collaborate with domain experts, product partners, and engineers on technical design, acceptance criteria, and documentation.