Carnot Research is hiring a GenAI/LLM Engineer
Join our rapidly growing AI engineering team as we build cutting-edge agentic systems, deploy production-ready LLMs, and create next-generation multimodal applications. If you're passionate about working with large language models, implementing agentic frameworks, and pushing the boundaries of AI capabilities, we'd love to connect with you.
Responsibilities
- Design and implement agentic systems using frameworks like LangChain, LlamaIndex, CrewAI, or AutoGPT for complex task automation.
- Build and optimize RAG (Retrieval Augmented Generation) pipelines with efficient vector storage, retrieval strategies, and context management.
- Fine-tune and adapt pre-trained language models for domain-specific use cases using techniques like LoRA, QLoRA, or full fine-tuning.
- Deploy and serve LLM applications in production environments with proper monitoring, error handling, and performance optimization.
- Work with prompt engineering and prompt optimization techniques to maximize model performance and reliability.
- Integrate multiple LLM APIs and manage fallback strategies, cost optimization, and response quality monitoring.
- Collaborate with product and engineering teams to translate business requirements into AI-powered solutions.
- Implement evaluation frameworks and benchmarking systems to measure model performance and quality.
- Build multimodal applications integrating text, voice, and vision capabilities.
- Stay updated with the latest research and implement state-of-the-art techniques in production systems.
Requirements
- Strong hands-on experience with LLM APIs including OpenAI, Anthropic, Google, or open-source alternatives.
- Solid understanding of transformer architectures, attention mechanisms, and modern LLM capabilities and limitations.
- Experience with at least one agentic framework like LangChain, LlamaIndex, or similar tools for building complex AI workflows.
- Practical knowledge of vector databases such as Pinecone, Weaviate, Qdrant, or Chroma for RAG implementations.
- Familiarity with fine-tuning techniques and frameworks like Hugging Face Transformers, Axolotl, or similar.
- Strong Python programming skills with experience in async operations, API development, and error handling.
- Understanding of prompt engineering principles, few-shot learning, and chain-of-thought reasoning.
- Experience with model evaluation metrics, testing frameworks, and quality assurance for LLM outputs.
- Knowledge of embeddings, semantic search, and similarity matching techniques.
- Bonus: Experience with voice AI, multimodal models, or computer vision integration. Problem-solving mindset with ability to debug complex AI system behaviors. One to three years of relevant experience in GenAI, LLM applications, or ML engineering, though we're flexible for exceptionally strong candidates.
What We Offer
- Opportunity to work on cutting-edge AI applications including agentic systems, voice agents, and multimodal platforms.
- Exposure to the complete AI product lifecycle from research to production deployment.
- Freedom to experiment with latest models, frameworks, and techniques in a fast-paced R&D environment.
- Collaborative culture working closely with ML researchers and product engineers.
- Access to compute resources and tools needed for model training and experimentation.
- Competitive compensation with equity options.
- Flexible work arrangements and strong focus on learning and growth.
- Direct impact on products used by real customers in production environments.
