LLM Application Engineer

We are seeking an experienced LLM Application Engineer to design, develop, and optimize innovative applications powered by Large Language Models (LLMs) and machine learning (ML) techniques. The ideal candidate will have 4+ years of experience in developing AI/ML-driven applications, with a strong background in natural language processing (NLP), deep learning, and software engineering. You will collaborate with product, engineering, and research teams to create impactful AI solutions that address real-world challenges and drive business growth.

Key Responsibilities:

- Design and build scalable applications using Large Language Models (e.g., GPT, BERT, LLaMA) and complementary ML models to solve business problems.

- Develop and maintain robust APIs and workflows for integrating LLMs and ML models into production applications.

- Fine-tune LLMs and train custom ML models for domain-specific use cases, ensuring high performance and accuracy.

- Implement advanced techniques such as prompt engineering, chain-of-thought reasoning, and retrieval-augmented generation (RAG).

- Collaborate with data engineers to preprocess, clean, and curate datasets for training and evaluation.

- Optimize LLMs and ML pipelines for performance, scalability, and cost-efficiency.

- Integrate AI models with external systems (e.g., databases, APIs, and knowledge bases) to provide dynamic application functionality.

- Monitor, evaluate, and improve the performance of LLM- and ML-based applications using metrics such as accuracy, relevance, and scalability.

- Research and propose innovative solutions incorporating state-of-the-art advancements in LLMs and ML into applications.

- Document workflows, technical designs, and deployment processes for seamless collaboration and scaling.

Qualifications:

Education & Experience:

- Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, or a related field.

- 4+ years of hands-on experience in developing and deploying AI/ML-powered applications, with a focus on LLMs and machine learning techniques.

Technical Skills:

- Proficiency in programming languages such as Python and JavaScript for application and model development.

- Strong experience with LLM frameworks and libraries like Hugging Face Transformers, LangChain, and OpenAI APIs.

- Proficiency with machine learning libraries such as Scikit-learn, TensorFlow, PyTorch, or Keras.

- Expertise in retrieval-augmented generation (RAG) techniques and vector databases (e.g., Pinecone, FAISS, Weaviate).

- Familiarity with data preprocessing, feature engineering, and annotation for ML and NLP tasks.

- Proficiency in deploying AI/ML solutions on cloud platforms (AWS, Azure, GCP).

- Knowledge of prompt engineering, model fine-tuning, and adaptive workflows for LLMs.

- Experience with MLOps practices, including CI/CD pipelines, monitoring, and model lifecycle management.

- Hands-on experience with containerization and orchestration tools like Docker and Kubernetes.

Soft Skills:

- Strong analytical and problem-solving skills, with a focus on creating practical, user-friendly solutions.

- Excellent collaboration and communication skills for working with cross-functional teams.

- Ability to lead projects and mentor junior team members in a fast-paced development environment.

Preferred Qualifications:

- Experience building conversational AI applications or chatbots using LLMs and ML techniques.

- Familiarity with multi-modal LLMs and integrating them into applications involving audio, image, or video inputs.

- Certifications in AI/ML technologies (e.g., AWS Certified Machine Learning, Hugging Face Certifications).

- Knowledge of ethical AI practices, including bias mitigation and responsible AI principles.

This role offers a unique opportunity to leverage your expertise in LLMs and machine learning to build cutting-edge applications that transform industries. If you're passionate about delivering impactful, scalable AI solutions, we want to hear from you!