Note: The job is a remote job and is open to candidates in USA. ELSA, Corp is a leading company in generative AI focused on improving English communication skills globally. They are seeking an AI Engineer to enhance their AI-driven language learning technologies by developing and deploying LLM-powered capabilities.
Responsibilities
- Design, build, and deploy AI-powered agents that utilize LLMs for reasoning, retrieval, and action-based workflows
- Implement intelligent evaluation and feedback loops to measure model performance and continuously improve AI-driven learning experiences
- Develop scalable AI pipelines and AI Ops workflows to accelerate research-to-production cycles
- Work with prompt engineering, fine-tuning, LLM orchestration frameworks, and model evaluation techniques to refine conversational experiences
- Collaborate cross-functionally with researchers, engineers, and product teams to integrate AI seamlessly into ELSAs platform
Skills
- Hands-on experience with LLM orchestration frameworks (LangChain, LlamaIndex, OpenAI function calling, or similar)
- Experience building agent-based AI systems that integrate multiple tools, APIs, or retrieval methods
- Strong experience deploying and iterating on AI applications, focusing on user impact rather than just model performance
- Proficiency in NLP, LLMs, and generative AI frameworks, with experience in both open-source tools like PyTorch, TensorFlow, Hugging Face, and transformer-based models, as well as closed-source models and platforms such as OpenAI, Anthropic, Gemini, DeepSeek, LangChain, and LangSmith
- Strong software engineering background, including experience with APIs, microservices, containerization (Docker, Kubernetes), and cloud services
- Experience with multi-step reasoning models and structured inference techniques (Chain-of-Thought, Tree-of-Thoughts, Graph-based reasoning)
- Hands-on experience with AI agent architectures, including self-improving, multi-agent collaboration tools like DSPy, CrewAI, or Microsoft Autogen
- Familiarity with memory-augmented AI, knowledge distillation techniques, and continual learning approaches for evolving AI models over time
- Strong knowledge of parameter-efficient fine-tuning (LoRA, QLoRA, PEFT) and model compression for efficient deployment
- Understanding of integrating LLMs with external APIs and structured retrieval systems, improving AI accuracy with hybrid search techniques
Benefits
- Experience the true spirit of a fast-growing and well-funded Silicon Valley startup.
- Fun energetic team; international and collaborative culture.
- Opportunities to grow professionally and play a critical role in shaping the next stage of the companys growth.
Company Overview