Responsibilities
- Design, develop, and optimize LLM-based services for code generation, test automation, and AI copilots.
- Implement RAG workflows to combine internal context (e.g., wikis, APIs, design specs) with LLM capabilities.
- Leverage agentic frameworks to enable AI systems to take intelligent actions (e.g., generate PR-ready code or suggest test coverage improvements).
- Collaborate with engineers, product managers, and platform teams to integrate solutions into VS Code, GitHub, and CI/CD pipelines.
- Own and evolve platform architecture, from prompt engineering to model orchestration and security compliance.
Requirements:
- LLM Integration & Prompt Engineering: Experience building applications on top of GPT-3/4, Claude, or similar.
- RAG Systems: Hands-on expertise in Retrieval-Augmented Generation pipelines, vector stores, and semantic search.
- Cloud Infrastructure: Strong AWS experience (Lambda, S3, EC2, IAM); IaC with Terraform or CloudFormation.
Deep Technical Proficiency
- Python & TypeScript/JavaScript (backend + integrations)
- PyTorch, Transformers, and HuggingFace
- Natural Language Understanding (NLU/NLP) for processing specs, wikis, and design inputs
- API Design, GitHub Webhooks, and VS Code extension APIs
Report job
