Ai Engineer - Performance Team

Coverflex Work changed. Pay didn t. Coverflex exists to make compensation work for everyone. Pay is still rigid, fragmented, and hard to feel. We turn compensation into choice - one platform, one card, one app - for benefits, meal allowance, insurance and more. Our platform is simple for HR and meaningful for employees. We provide choice, smarter compensation tools and empowerment. TL;DR (The Essentials) Role: AI Engineer Seniority Level: Mid Type: Individual Contributor Languages: English (main) / Portuguese, Spanish or Italian a plus Main Tools: OpenAI API Vercel SDK or similar Langsmith / Braintrust / Langfuse or similar Cursor / Codex / Claude Code Location: Remote (Europe only) Compensation: • Base Salary: 40K to 60K gross annually • Equity: Yes - VSOPs • Benefits: See below • Contract Type:Permanent Your Impact Your role will play a major role in our success because... With our goals to scale AI, specially for expansion post-series B, we need AI that has some minimum threshold of reliability. Our AI already handles thousands of conversations per week and we expect that to increase significantly. We need dedicated effort in making sure that our AI is accurate, helpful and reliable. You ll know you re successful when, after 90 days, you ve... 1. Maintain evals to keep close to 100% accuracy and update them as we get new feedback 2. Monitor user feedback to ensure our agents have a high level of accuracy 3. Run new experiments to proactively increase the performance of current agents (test new prompts, models, agent architectures) 4. Keep up to date with AI developments 5. Design new agents 6. Maintain Evals infrastructure to run reliably and at reasonable time and cost in our CI/CD pipeline How we ll measure success: 1. Eval coverage exists for all production agents. Evals are updated shortly after new feedback. Accuracy stays above agreed threshold and matches real-world performance. 2. Feedback loop is active - issues are caught and logged. Time to detect accuracy problems decreases. Recurring issues are identified and addressed. 3. Number of experiments ran and documented per month, resulting in improvements shipped to production. 4. New agents go from concept to production. Agents meet quality bar on first iterations (fewer back-and-forth cycles). Reality Check - What Makes This Role Hard Let's be real - here's what makes this role challenging: Biggest hurdle is the fact that this is a new field. Processes are being created and it requires faster adaptation to new developments in the industry. Also relevant is that we LLMs are inherently non-deterministic which can make the work more complex than with software. You Must-haves (evidence, not years) Functional coding in TypeScript or Python Demonstrated experience with LLMs (personal project or professional) Experience with creating AI agents Familiarity with LLM providers and model trade-offs Nice-to-have Exposure to LLM observability tools Experience with OSS models Background in SW, product, QA, or data Your DNA Genuinely curious about AI - explores new models and tools for fun, not just work. More excited about making the model perform well than writing elegant code. Comfortable with ambiguity and iteration. Testing mindset: likes to measure, compare, and improve. Proactive in sharing findings and documenting learnings. Who will probably find this frustrating... Someone who sees this as a stepping stone to "real" ML/infra engineering. Pure coders who want to build systems but have no patience for prompt iteration. People who need clear specs to start working - this role requires experimentation. Anyone who thinks prompt engineering is "not real work". Manager & Team Meet Your Manager Hiring Manager: F bio Domingues, Senior AI Engineer Location: Portugal LinkedIn Profile:https://www.linkedin.com/in/fjrdomingues/ Profile Snapshot: • Energy:Calm and steady. I genuinely enjoy the work - solving problems, making progress, seeing things improve. No artificial urgency or drama. I like to keep things relaxed while still moving forward. • Communication: Straightforward and low-ceremony. I value clarity over polish. I might skip the small talk and get straight to the point - not because I don't care, just because that's how I'm wired. I'm always open to questions and back-and-forth. • Feedback Style:Honest and collaborative. If something isn't working, I'll say it - but constructively, and I'll help fix it. I appreciate direct feedback in return. No egos, no politics How to work with me - in the Manager's own words: Relaxed but engaged. We'll share the workload, think through problems together, and iterate quickly. I don't have rigid processes - you'll have room to shape how we work. If you like autonomy, ownership, and a calm environment where the focus is on doing good work, we'll get along well. Your Team You ll work day-to-day with: • Engineers, Product Manager, Product Designer, Engineering Mana...