Info on the LLM Engineer role
Want to get to the next step in your international career? We can support you!
Ubiminds is a GPTW certified, people-first company that partners with American software product companies to scale their development footprint. Ubi custom-curates Brazilian top 5% talent for their LATAM strategy, offering a unique combo of staff augmentation and employer-of-record services.
Ubiminds is assisting a global rating agency established to restore trust in credit ratings and offer accurate and transparent ratings.
Challenge
We are looking for an experienced LLM Engineer to design, build, and deploy features for Gen AI-driven applications. The role requires strong Python skills, experience with large language models, and a collaborative approach to deliver scalable and reliable AI solutions alongside cross-functional teams.
What you'll do
LLM Integration and Deployment:
- Integrate LLM models with frameworks to support production-grade systems.
- Develop prompt chains, agents, and related tools to enable seamless interaction with LLMs.
- Ensure scalability, security, observability, and reliability in LLM capabilities.
Performance Monitoring and Optimization:
- Monitor and analyze the performance of deployed LLM features.
- Optimize LLM results for accuracy, computational efficiency, speed, and cost-effectiveness.
Research and Exploration:
- Stay up to date on the latest advancements in Generative AI, LLMs, NLP, and ML.
- Rapidly prototype and evaluate new techniques to push the capabilities of LLM solutions.
Collaboration:
- Work closely with cross-functional teams to align technical solutions with business objectives.
- Collaborate with prompt engineers and software developers to operationalize LLM features as part of a “Gen AI Factory.”
In order to succeed in this position, you will need:
Mandatory skills
- Advanced/fluent English skills – Excellent written and verbal communication skills.
- Strong experience in Python development, including familiarity with AI and ML libraries.
- Hands-on experience delivering LLM solutions to production.
- Proficiency with LLM frameworks and related technologies (e.g., OpenAI API, LangChain, Hugging Face).
- Experience with vector embeddings and Retrieval-Augmented Generation (RAG) solutions.
- Knowledge of relational databases (Snowflake preferred) and proficiency in integrating them into AI solutions.
- Strong problem-solving skills, attention to detail, and a focus on scalable architecture.
Nice to have
- Experience with cloud platforms such as AWS, Azure, or Google Cloud.
- Familiarity with MLOps/LLMOps practices and tools (e.g., Weights & Biases).
- Experience with fine-tuning LLMs, including reinforcement learning techniques like RLHF.
- Knowledge of containerization and orchestration tools (e.g., Docker, Kubernetes).
- Proficiency in working with RESTful APIs, microservices architecture, and CI/CD pipelines.
- Exposure to parsing frameworks (e.g.,
Unstructured.io) and graph databases.
Non-technical skills
• Excellent communication skills, with the ability to explain technical concepts to non-technical stakeholders.
• Collaborative mindset to work effectively in cross-functional teams.
• Adaptability and eagerness to learn new technologies and improve existing skills.
• Strong critical thinking and self-motivation to deliver innovative solutions.
About Ubiminds
Our Culture
People First. We are all about people!
Challenge yourself. There’s always room for improvement and continuous improvement is in our essence.
Make it happen. Be ready to take challenges as they come. It’s all about attitude and commitment.
We’re in this together. We work as a team, thrive as a team, and evolve as a team.
Averaging on awesome. We work hard to deliver high-quality services and look forward to exceeding expectations.
Keep it real. We promise you honesty, transparency, and openness, regardless of the situation.
Perks and Benefits
As LLM Engineer @Ubiminds, you:
- Are placed in a product-based company, with the same treatment as their full-time employees.
- Have our full back-office support, from career guidance to HR and concierge services.
- Enjoy our remote-first policy – we are a distributed team, after all.
- Get your own MacBook (none of that "bring your own device" stuff here).
- Have access to growth opportunities with other amazing technology professionals, through tech talks, chapter meetings, and even remote happy hours for tons of fun!
- Improve your English through free lessons with a native English speaker - get to the next level on your communication skills!
- Miss working in the office? Our cool Florianópolis headquarters is available, whenever you want, with weekly quick massages & tasty snacks, soft drinks, and games
How our process works
1. Interview with Tech Recruiter (chat about the job opening and your experiences)
2. Client process (this may vary)
3. Offer (yay)
