Generative AI / LLM Engineer
Triunity Software
yesterday
Role details
Contract type
Permanent contract Employment type
Full-time (> 32 hours) Working hours
Regular working hours Languages
English Experience level
SeniorJob location
Tech stack
API
Artificial Intelligence
Amazon Web Services (AWS)
Automated Storage and Retrieval Systems
Computer Programming
Information Retrieval
Python
Software Safety
Large Language Models
Multi-Agent Systems
Prompt Engineering
Generative AI
Build Management
GPT
Microservices
Job description
We are looking for a skilled Generative AI / LLM Engineer to design, develop, and deploy intelligent applications powered by large language models. The ideal candidate will have hands-on experience with modern LLM frameworks, evaluation tools, and cloud-based AI services, along with a strong understanding of retrieval-augmented generation (RAG) systems., * Design and build end-to-end LLM-powered applications using LangChain and LangGraph
- Develop scalable workflows for complex reasoning, tool usage, and multi-agent systems
- Implement RAG pipelines using AWS OpenSearch for efficient information retrieval
- Integrate foundation models via AWS Bedrock for production-grade AI solutions
- Monitor, evaluate, and improve model performance using LangSmith and Arize Phoenix
- Optimize prompts, chains, and workflows for accuracy, latency, and cost
- Collaborate with cross-functional teams to translate business requirements into AI solutions
- Ensure best practices in AI safety, observability, and performance tracking
Requirements
- Strong experience with LangChain and LangGraph
- Hands-on experience with LangSmith and Arize Phoenix for LLM evaluation
- Experience working with AWS Bedrock and deploying cloud-based AI solutions
- Proficiency in AWS OpenSearch for building search and retrieval systems
- Solid understanding of RAG architectures and prompt engineering
- Programming skills in Python
- Familiarity with APIs, microservices, and scalable system design
