LLM Engineer

​

Core Technical Skills:

LLM Fundamentals & Architecture

• Deep understanding of transformer architectures, attention mechanisms, and how modern LLMs process information.

• Knowledge of different model families (GPT, Claude, Llama, Mistral, etc.) and their architectural differences.

• Understanding of tokenization, embeddings, context windows, and temperature/sampling parameters.

• Familiarity with fine-tuning techniques: full fine-tuning, LoRA, QLoRA, PEFT methods

• Knowledge of quantization (4-bit, 8-bit) and model compression techniques

Prompt Engineering & Context Management

• Expert-level prompt engineering including chain-of-thought, few-shot learning, and retrieval-augmented generation (RAG).

• Experience with prompt optimization frameworks and evaluation.

• Understanding of context window management and strategies for long-context applications.

• Knowledge of system prompts, role-playing, and structured output generation.
   

Development Stack

• Strong Python programming with focus on ML/AI libraries.

• Experience with LLM frameworks: LangChain, LlamaIndex, Semantic Kernel, or Haystack.

• API integration experience with OpenAI, Anthropic, Cohere, or other LLM providers.

• Vector database experience: Pinecone, Weaviate, Chroma, FAISS, Qdrant.

• Orchestration tools: LangGraph, CrewAI, or custom agentic frameworks.
   

Qualifications:

• Experience 3+ years of experience in software development.

• Fluent English - Required (C1)

• Professional training in computer science or related fields - Preferred.
   

About the job:

• Remote (US time zone).

• Full time.

• Payment in USD.

• Salary depends on skills.