Log in or sign up (free) to apply to this job.
About the role
Required Skills & Qualifications
● Strong hands-on experience with LLM frameworks and models, including LangChain,
OpenAI (GPT-4), and LLaMA
● Proven experience in LLM orchestration, workflow management, and multi-agent
system design using frameworks such as LangGraph
● Strong problem-solving skills with the ability to propose end-to-end solutions and
contribute at an architectural/system design level
● Experience building scalable AI-backed backend services using FastAPI and
asynchronous programming patterns
● Solid experience with cloud infrastructure on AWS, including EC2, S3, and Load
Balancers
● Hands-on experience with Docker and containerization for deploying and managing
AI/ML applications
● Good understanding of Transformer-based architectures and how modern LLMs work
internally
● Strong skills in data processing and analysis using NumPy and Pandas
● Experience with data visualization tools such as Matplotlib and Seaborn for analysis
and insights
● Hands-on experience with Retrieval-Augmented Generation (RAG), including
document ingestion, embeddings, and vector search pipelines
● Experience in model optimization and training techniques, including fine-tuning,
LoRA, and QLoRA
Nice to Have / Preferred
● Experience designing and operating production-grade AI systems
● Familiarity with cost optimization, observability, and performance tuning for
LLM-based applications
● Exposure to multi-cloud or large-scale AI platforms
Skills required
Ready to apply?
Create a free account to apply and tailor your resume to this role.
Apply on Appiness Interactive