Senior AI Engineer - Chat & Agent Systems

We are looking for an experienced AI Engineer to take a leading technical role in the development of advanced chat and agent-based systems. In this hands-on position, you will shape technical direction, own system design, and contribute directly to production Python development. You will translate product requirements into reliable, maintainable solutions while raising engineering standards across the team. You will also mentor junior engineers, guide architectural decisions, and strengthen code quality through thoughtful reviews. A key part of the role will be advancing the team's use of AI coding agents throughout the software development lifecycle. This is an opportunity to combine strong software engineering fundamentals with practical expertise in building and operating production-grade agentic applications.

The ideal candidate combines strong software engineering fundamentals with hands-on experience building LLM-powered applications and using AI coding agents. The following qualifications and skills are expected:

• Approximately 4–5 years of professional software engineering experience.

• Strong proficiency in Python, including idiomatic, typed, testable, and maintainable production code.

• Solid programming fundamentals and consistently sound engineering judgment.

• Experience designing, delivering, and operating production systems.

• Strong understanding of API design, data modeling, concurrency, error handling, and observability.

• Ability to create useful abstractions while keeping systems simple and understandable.

• Experience writing automated tests using tools such as pytest.

• Ability to conduct meaningful code reviews and clearly explain technical recommendations.

• Experience mentoring junior developers and helping improve their engineering capabilities.

• Strong ownership, initiative, problem-solving skills, and the ability to drive improvements across a team.

• Clear written and verbal communication skills.

Hands-on experience building LLM-powered or agentic applications is required. Relevant experience includes:

• Building tool-calling or multi-step workflows using LangGraph or comparable agent frameworks.

• Designing conversation state, context management, and execution flows.

• Working with model APIs, structured outputs, retrieval, and grounding techniques.

• Supporting streaming responses and asynchronous execution.

• Evaluating prompts, models, and end-to-end agent behavior.

• Instrumenting and debugging LLM applications with Langfuse, LangSmith, or similar observability platforms.

• Managing the reliability, latency, and cost of production LLM systems.

Expertise in every named tool is not expected. A strong understanding of the underlying engineering principles and the ability to adapt as the ecosystem evolves are more important.

The candidate should be highly proficient in agentic coding workflows and understand how to use coding agents as engineering tools rather than simply as code generators. This includes:

• Using coding agents effectively for exploration, planning, implementation, testing, debugging, and code review.

• Providing agents with appropriate context, constraints, and verification steps.

• Critically evaluating generated code for correctness, security, maintainability, and unnecessary complexity.

• Designing development workflows that ensure engineers remain accountable for the code produced.

• Identifying repeatable team processes that can be improved through agents and automation.

• Teaching junior developers to use coding agents effectively without compromising their engineering fundamentals.

• Leading practical initiatives that improve development speed and help establish AI-native engineering practices.

Success in this role will be reflected in clearer technical decisions, simpler system designs, stronger test coverage, more effective code reviews, and increasingly independent junior developers. You will also help make production issues easier to diagnose and resolve, establish responsible AI-assisted development practices, and improve the long-term maintainability and reliability of the codebase.