LLM Engineer - (Hybrid- Greenfield AI Project)
Core
Design and deploy generative AI systems including intelligent chatbots, agentic AI frameworks, RAG pipelines, and multimodal experiences leveraging transformer-based architectures.
Role type
Generative AI/LLM Engineer
Builds
Intelligent chatbots, agentic AI frameworks, RAG pipelines, multimodal experiences
Domain
Generative AI, Large Language Models, NLP
Deliverable
production ML models
Required skills
Transformer architectures, attention mechanisms, tokenization, Python, Hugging Face Transformers, LangChain, OpenLLM, vector databases (Pinecone, Weaviate, FAISS), prompt engineering, RAG, agent frameworks, function tooling, distributed computing, GPU acceleration, inference optimization
Preferred skills
None stated
Technologies
OpenAI, Azure OpenAI, AWS SageMaker, Google Vertex AI, Pinecone, Weaviate, FAISS, Hugging Face Transformers, LangChain, OpenLLM
Responsibilities
Build custom pipelines for RAG, embeddings, prompt tuning, and chain-of-thought reasoning; Design agentic workflows using frameworks like OpenAI's Agents SDK or LangChain; Craft robust prompts for diverse tasks and use few-shot/prompt-chaining techniques; Evaluate LLM output quality, safety, and latency through automated and human feedback loops; Integrate LLMs with internal systems, APIs, relational databases, NoSQL databases, vector databases, and real-time inference stacks; Partner with engineering teams, designers, and product leads to define use cases and success criteria
Seniority
Mid-level (1-3 years GenAI + 3-5 years ML)