At a Glance
- Tasks: Define and measure how LLMs use tools and orchestrate workflows.
- Company: Join a cutting-edge tech company leading in AI innovation.
- Benefits: Competitive salary, flexible work options, and opportunities for growth.
- Other info: Dynamic environment with a focus on innovative solutions.
- Why this job: Tackle exciting research challenges and shape the future of AI.
- Qualifications: Expertise in API design, model evaluation, and engineering.
The predicted salary is between 80000 - 100000 £ per year.
About the role
As a Model Behavior Architect on the Function Calling team, you are at the forefront of defining and measuring how LLMs use tools, invoke functions, and orchestrate complex agentic workflows. We are looking for people who have built a career in engineering, machine learning, and large language models and are experts in model evaluation, policy writing, and creating eval pipelines for tool use and function calling. Your role is to work hand‑in‑hand with our Science team to define what "good" looks like for function calling—from accurate parameter selection and schema adherence to multi‑step tool orchestration, error recovery, and agentic reasoning. Join us if you are passionate about tackling cutting‑edge, open‑ended research challenges and transforming your insights into best‑in‑class models.
What you will do
- Interact with models to identify where function calling and tool use behaviour can be improved
- Gather internal and external feedback on tool‑calling behaviour to scope areas for improvement
- Design and implement evals, data guidelines, data generation, and synthetic tool environments and APIs
- Identify and fix edge case behaviours, such as malformed arguments, hallucinated functions, and incorrect tool selection—through rigorous testing
- Develop robust evaluation pipelines for the function‑calling capabilities of our model candidates
- Work collaboratively with AI Scientists
About you
- You have a deep understanding of either 1) API design, structured outputs, and schema specification (e.g. JSON Schema), 2) engineering and code behaviour, 3) LLM agents at work, including reasoning, planning, and multi‑step tool use
- You have prior knowledge in training and optimising model behaviour
- You are an expert at building robust evaluations
- You thrive in dynamic and technically complex environments
- You have a track record of delivering innovative, out‑of‑the‑box solutions to address real‑world constraints
Model Behavior Architect- Function Calling employer: Neura Market
As a Model Behavior Architect at our innovative company, you will be part of a dynamic team that thrives on pushing the boundaries of machine learning and large language models. We offer a collaborative work culture that encourages creativity and continuous learning, with ample opportunities for professional growth in a cutting-edge field. Located in a vibrant tech hub, our company provides unique advantages such as access to industry-leading resources and a network of like-minded professionals dedicated to transforming research insights into impactful solutions.
StudySmarter Expert Advice🤫
We think this is how you could land Model Behavior Architect- Function Calling
✨Tip Number 1
Network like a pro! Reach out to folks in the industry, attend meetups, and connect with people on LinkedIn. You never know who might have the inside scoop on job openings or can put in a good word for you.
✨Tip Number 2
Show off your skills! Create a portfolio or GitHub repository showcasing your projects related to model evaluation and function calling. This gives potential employers a taste of what you can do and sets you apart from the crowd.
✨Tip Number 3
Prepare for interviews by brushing up on your technical knowledge and problem-solving skills. Practice common interview questions related to LLMs and function calling, and be ready to discuss your past experiences and how they relate to the role.
✨Tip Number 4
Don’t forget to apply through our website! It’s the best way to ensure your application gets seen by the right people. Plus, it shows you’re genuinely interested in joining our team at StudySmarter.
We think you need these skills to ace Model Behavior Architect- Function Calling
Some tips for your application 🫡
Show Your Passion:When writing your application, let your enthusiasm for model behaviour and function calling shine through. We want to see that you’re genuinely excited about tackling cutting-edge challenges in the field!
Tailor Your Experience:Make sure to highlight your relevant experience in engineering, machine learning, and large language models. We’re looking for specific examples of how you've tackled similar problems or projects in the past.
Be Clear and Concise:Keep your application clear and to the point. We appreciate well-structured responses that get straight to the heart of your skills and experiences without unnecessary fluff.
Apply Through Our Website:Don’t forget to submit your application through our website! It’s the best way for us to receive your details and ensures you’re considered for this exciting role.
How to prepare for a job interview at Neura Market
✨Know Your Models
Make sure you brush up on your knowledge of large language models and their function calling capabilities. Be ready to discuss specific examples of how you've improved model behaviour in the past, especially in terms of API design and structured outputs.
✨Showcase Your Evaluation Skills
Prepare to talk about your experience with building robust evaluation pipelines. Think of concrete instances where you've designed evals or data guidelines, and be ready to explain your thought process behind them.
✨Collaborate Like a Pro
Since this role involves working closely with AI Scientists, highlight your teamwork skills. Share examples of successful collaborations and how you’ve contributed to dynamic projects in technically complex environments.
✨Tackle Edge Cases
Be prepared to discuss how you've identified and fixed edge case behaviours in previous roles. Bring up specific challenges you've faced, such as dealing with malformed arguments or hallucinated functions, and how you approached solving them.
