- Location
- Colombo
- Type
- Full-time
- Department
- Engineering
- Seniority
- Senior
- Closing date
- Today
- Source
- CareersPage
Description
About the role
Build and ship production-grade applications powered by large language models and generative AI.
Responsibilities
- Design and build LLM-powered applications such as RAG systems, chatbots and content generation tools
- Develop prompts, retrieval pipelines and evaluation frameworks
- Fine-tune or adapt models where needed
- Integrate LLM APIs and open-source models into existing products
- Monitor quality, latency, cost and safety, and add guardrails
- Work closely with product and engineering teams to deliver use cases end to end
Requirements
- Strong Python and software engineering fundamentals
- Hands-on experience with LLM APIs (OpenAI, Anthropic, Gemini or similar) and frameworks such as LangChain or LlamaIndex
- Proven experience building RAG systems with embeddings and vector databases (Pinecone, pgvector, FAISS or similar)
- Experience evaluating LLM outputs and reducing hallucinations
- Experience with REST APIs, cloud deployment and Git
- Degree in Computer Science, Engineering or a related field
Nice to have
- Fine-tuning experience (LoRA, PEFT) with Hugging Face
- Agent frameworks (LangGraph, CrewAI) and tool calling
- Knowledge of LLM observability tools and prompt versioning
- Experience with multimodal models
Skills
PythonGitREST