Overview
We are seeking a skilled Generative AI Developer to design, build, and deploy AI-powered applications using large language models (LLMs) and other generative models. You will work on cutting-edge solutions involving text, code, image, and multimodal generation to solve real-world problems.
Key Responsibilities
- Design and develop applications using LLMs (e.g., GPT, open-source models)
- Build and optimize prompts, chains, and AI workflows
- Fine-tune and evaluate models for domain-specific use cases
- Develop APIs and backend systems integrating AI capabilities
- Work with vector databases and embeddings for retrieval-augmented generation (RAG)
- Ensure scalability, performance, and cost-efficiency of AI systems
- Implement guardrails for safety, bias mitigation, and responsible AI usage
- Collaborate with product, data, and engineering teams
Required Skills & Qualifications
- Strong programming skills in Python (preferred) or JavaScript
- Experience with LLM frameworks (e.g., LangChain, LlamaIndex)
- Familiarity with APIs from providers like OpenAI, Anthropic, etc.
- Understanding of NLP concepts and transformer architectures
- Experience with REST APIs, microservices, and cloud platforms (AWS, Google Cloud Platform, or Azure)
- Knowledge of vector databases (e.g., Pinecone, Weaviate, FAISS)
- Version control (Git) and software engineering best practices
Preferred Qualifications
- Experience fine-tuning open-source models (e.g., LLaMA, Mistral)
- Knowledge of prompt engineering techniques and evaluation methods
- Familiarity with MLOps tools and deployment pipelines
- Experience with multimodal AI (image, audio, video)
- Background in machine learning or data science
Tools & Technologies
- Languages: Python, JavaScript
- Frameworks: LangChain, LlamaIndex, FastAPI
- AI Models: GPT, Claude, LLaMA, Mistral
- Databases: Vector DBs, SQL/NoSQL
- Cloud: AWS, Azure, Google Cloud Platform
- DevOps: Docker, Kubernetes (optional)