AI Engineer – Agentic AI & RAG
About the role
The AI Engineer – Agentic AI & RAG role focuses on designing and developing advanced agentic systems and Retrieval-Augmented Generation (RAG) pipelines. The position involves building and deploying production-grade large language model (LLM) applications, developing evaluation and monitoring frameworks, and enhancing system safety and robustness. The engineer will also be responsible for model deployment, scaling, API design, and collaborating with stakeholders to deliver measurable machine learning outcomes. Mentoring team members and contributing to engineering standards are also key aspects of the role. Candidates should have a strong background in software or machine learning engineering, hands-on experience with LLM-based products, and proficiency in Python and modern software engineering practices.
Must have
- Minimum 2 years of experience in software or machine learning engineering with a proven record of deploying ML systems to production.
- Engineering degree in Computer Science, Electronics, Machine Learning, or a related field.
- Strong hands-on experience building LLM-based products including agents, RAG systems, tool calling, and structured generation.
- Proficiency in Python and solid software engineering practices including clean architecture, testing, and CI/CD.
- Experience with vector databases and search technologies such as pgvector, Pinecone, Weaviate, FAISS, Elasticsearch, or OpenSearch.
- Understanding of distributed systems and production constraints including latency, cost, reliability, and security.
- Practical knowledge of LLM evaluation methodologies and regression prevention.
- Strong communication skills with the ability to lead workstreams end-to-end.
Nice to have
- Experience with model fine-tuning or adaptation (SFT, LoRA/QLoRA) and inference frameworks such as vLLM, TGI, or Triton.
- Familiarity with knowledge graphs and structured knowledge systems (RDF/OWL, Neo4j, entity linking).
- Experience in document AI and multimodal extraction, including OCR, layout understanding, and form/table processing.
- Exposure to compliance-heavy domains such as healthcare or finance with privacy and security considerations.
- Experience with agent frameworks such as LangGraph, Autogen, and Semantic Kernel, and orchestration patterns.
Technologies
- Agentic AI
- AutoGen
- CI/CD
- Elasticsearch
- Embeddings
- FAISS
- Fine-Tuning
- LangGraph
- LLM
- Machine Learning
- Model Deployment
- Neo4j
- Observability
- OpenSearch
- pgvector
- Pinecone
- Prompt Engineering
- Python
- RAG
- Semantic Kernel
- Triton
- Vector Databases
- vLLM
- Weaviate
Jobs across Sri Lanka, watched for you.Colombo, Sri Lanka