Job Description: 1. Build production-ready AI applications using Python and FastAPI.
2. Design LLM pipelines including data ingestion, inference, and response generation.
3. Leverage GCP tools like Vertex AI, Cloud Run/Functions, BigQuery, and Cloud Storage.
4. Apply advanced prompt engineering techniques to enhance LLM outputs.
5. Implement vector stores and embeddings for semantic search and RAG.
6. Use orchestration frameworks (e.g., LangChain, LangGraph, CrewAI) for complex workflows.
7. Integrate AI systems with enterprise platforms and maintain robust data flows.
8. Follow best practices in coding, testing, and deployment within CI/CD pipelines.
9. Continuously explore and recommend emerging tools and AI technologies.
Responsibilities: 1. 2+ years of experience developing AI solutions, especially with LLMs.
2. Proficient in Python and FastAPI for API development.
3. Hands-on experience with GCP services (Vertex AI, Cloud Run/Functions, etc.).
4. Strong prompt engineering skills (e.g., CoT, few-shot, instruction tuning).
5. Experience with vector databases and RAG systems.
6. Familiarity with LLM orchestration frameworks.
7. Solid understanding of software engineering fundamentals.
8. Proficient with Git and CI/CD practices.
Qualifications: 1. Bachelors or Masters in Computer Science
2. Experience with MLOps for model deployment and monitoring.
3. Knowledge of distributed systems and data processing.
4. Contributions to open-source projects or strong AI project portfolio.
5. Strong communication skills and ability to explain technical concepts clearly.
