Senior AI Engineer

Stott and May Inc.; München; Hybrid; EUR 90,000 - 110,000; Full time

Job summary

Stott and May Inc. is seeking a Senior AI Engineer to own agent quality, building and improving LLM agents in Python with a focus on orchestration, evaluation and reliable production performance.

You will handle model selection, prompting and context engineering, plus evaluation, benchmarking and harnessing. Munich preferred with remote within Germany possible; English-speaking team and equity opportunity.

Qualifications

• Strong Python experience.
• Production experience building LLM/AI agents.
• Experience with evals, benchmarking or AI quality.
• Strong technical ownership and product judgement.
• Track record of shipping and improving AI systems with data.

Responsibilities

• Build and improve LLM agents in Python.
• Model selection, prompting and context engineering.
• Evaluation, benchmarking and agent harnesses.
• Turn real conversations into test cases.
• Find failure modes and ship measurable improvements.

Skills

Python

LLM/AI agents

evals/benchmarking

ownership/product judgement

shipping AI systems with data

Job description

Help to build AI agents that handle real customer interactions for field sales teams - across chat and voice. This startup already has 2,000 B2B customers, including enterprises with 10,000+ employees.

We’re hiring a Senior AI Engineer to own agent quality.

What you’ll own

• Build and improve LLM agents in Python
• Model selection, prompting and context engineering
• Evaluation, benchmarking and agent harnesses
• Turn real conversations into test cases
• Find failure modes and ship measurable improvements

This is about orchestrating and evaluating models - not training them.

What we're looking for

• Strong Python
• Production experience building LLM / AI agents
• Experience with evals, benchmarking or AI quality
• Strong technical ownership and product judgement
• A track record of shipping and improving AI systems with data

Experience with voice agents, realtime AI or multilingual agents is a plus.

Why this role?

You’ll own a mission-critical part of the product from day one, with significant autonomy and direct impact on how the agent performs in production.

Munich preferred. Remote within Germany is possible. English-speaking team.

€90–110k base + meaningful equity. More for exceptional candidates.