LLM Engineer

BrothersTech; United States; On-site; USD 150,000 - 210,000; Full time

Job summary

BrothersTech is seeking an experienced engineer to design and develop LLM-powered applications in a fast-paced AI-focused environment.

You will build RAG pipelines, implement prompt strategies, and integrate models with enterprise data and APIs while coordinating with data scientists and product teams. The role demands deep knowledge of NLP, software engineering, and scalable AI systems.

Qualifications

• Proficient in Python and NLP with hands-on experience in Generative AI.
• Experience building RAG systems, embeddings, and semantic search.
• Knowledge of OpenAI APIs, Claude, Gemini, and open-source models; familiar with LangChain/LangGraph/LlamaIndex.

Responsibilities

• Design and develop LLM-powered applications using commercial and open-source language models.
• Build and optimize Retrieval-Augmented Generation (RAG) pipelines.
• Implement prompt engineering, context management, and response optimization techniques.
• Integrate LLMs with enterprise applications, APIs, and data sources.
• Work with vector databases and embedding models for semantic search.
• Develop AI agents and tool-calling workflows for automated tasks.
• Fine-tune and evaluate LLMs for domain-specific applications.
• Optimize latency, scalability, accuracy, and inference costs.
• Implement guardrails, responsible AI practices, and data privacy controls.
• Collaborate with data scientists, software engineers, and product teams.
• Monitor deployed AI systems and improve performance using evaluation metrics.
• Maintain documentation, testing standards, and deployment pipelines.

Skills

Python programming

NLP and Generative AI

Prompt engineering

English communication

Education

Bachelor's or Master’s in CS/AI/Data Science

Tools

OpenAI APIs

Anthropic Claude

Google Gemini

LangChain

LangGraph

LlamaIndex

Pinecone

Weaviate

Chroma

FAISS

Git

Docker

AWS/Azure/GCP

Job description

• Design and develop LLM-powered applications using commercial and open-source language models.
• Build and optimize Retrieval-Augmented Generation (RAG) pipelines.
• Implement prompt engineering, context management, and response optimization techniques.
• Integrate LLMs with enterprise applications, APIs, and data sources.
• Work with vector databases and embedding models for semantic search.
• Develop AI agents and tool-calling workflows for automated tasks.
• Fine-tune and evaluate LLMs for domain-specific applications.
• Optimize latency, scalability, accuracy, and inference costs.
• Implement guardrails, responsible AI practices, and data privacy controls.
• Collaborate with data scientists, software engineers, and product teams.
• Monitor deployed AI systems and improve performance using evaluation metrics.
• Maintain documentation, testing standards, and deployment pipelines.

Required Skills

• Strong programming experience in Python.
• Hands-on experience with LLMs, Generative AI, and NLP.
• Experience with OpenAI APIs, Anthropic Claude, Google Gemini, or open-source models.
• Knowledge of LangChain, LangGraph, or LlamaIndex.
• Experience building RAG systems, embeddings, and semantic search.
• Familiarity with vector databases such as Pinecone, Weaviate, Chroma, or FAISS.
• Knowledge of transformer architectures and attention mechanisms.
• Familiarity with SQL, NoSQL databases, and data processing.
• Experience with Git, Docker, and cloud platforms such as AWS, Azure, or GCP.

Preferred Qualifications

• Experience with LLM fine-tuning, LoRA, or QLoRA.
• Knowledge of Hugging Face Transformers and model-serving frameworks.
• Experience with AI agents, function calling, and multi-agent systems.
• Familiarity with model evaluation, hallucination reduction, and AI safety.
• Experience deploying scalable AI workloads using Kubernetes or serverless services.
• Knowledge of GPU inference optimization and quantization.

Education

Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Data Science, or a related field, or equivalent practical experience.