AI / LLM Engineer – OrcaWorks AI

Qualifications

• Master’s degree (or Bachelor’s with equivalent experience) in AI, Computer Science, or ML
• Strong grasp of transformer architectures, embeddings, and NLP concepts
• Hands-on experience with Hugging Face Transformers, LangChain, and vector databases (Vespa, Pinecone, FAISS)
• Familiarity with FastAPI, SQLModel, and MLOps tools for deployment
• Programming experience in Python (PyTorch/TensorFlow)
• Curiosity and drive to explore applied generative AI and orchestration workflows

Responsibilities

• Develop, fine-tune (lightweight), and evaluate LLMs for business and workflow automation use cases
• Implement prompt engineering, retrieval-augmented generation (RAG), and context-aware AI pipelines
• Integrate with agent frameworks (AutoGen, LangChain, CrewAI) and collaborate with backend teams on FastAPI-based services
• Conduct model performance analysis, error tracking, and iterative improvements
• Explore and operationalize open-source models (Llama, GPT, Mistral) in production environments

Full Description

Location: Hybrid / Atlanta, GA

Experience Level: Entry-level (Master’s preferred)

About OrcaWorks AI

At OrcaWorks AI, we specialize in the design and deployment of applied AI and LLM solutions that transform how businesses operate.

We’re seeking LLM Engineers excited to integrate intelligent models into production systems, experiment with context workflows, and enable next-gen automation.

KeyResponsibilities

• Develop, fine-tune (lightweight), and evaluate LLMs for business and workflow automation use cases.

• Implement prompt engineering, retrieval-augmented generation (RAG), and context-aware AI pipelines.

• Integrate with agent frameworks (AutoGen, LangChain, CrewAI) and collaborate with backend teams on FastAPI-based services.

• Conduct model performance analysis, error tracking, and iterative improvements.

• Explore and operationalize open-source models (Llama, GPT, Mistral) in production environments.

Required Skills & Qualifications

• Master’s degree (or Bachelor’s with equivalent experience) in AI, Computer Science, or ML.

• Strong grasp of transformer architectures, embeddings, and NLP concepts.

• Hands-on experience with Hugging Face Transformers, LangChain, and vector databases (Vespa, Pinecone, FAISS).

• Familiarity with FastAPI, SQLModel, and MLOps tools for deployment.

• Programming experience in Python (PyTorch/TensorFlow).

• Curiosity and drive to explore applied generative AI and orchestration workflows.