GenAI/Python Developer - AI/ML - Newyork, NY - Citi

Key Responsibilities

• Design, develop, and orchestrate sophisticated Generative AI workflows using LangGraph, LangChain, and multi-agent architectures.
• Build and maintain advanced Retrieval-Augmented Generation (RAG) solutions using LlamaIndex and vector databases.
• Design retrieval pipelines focused on improving the accuracy and relevance of LLM-generated responses.
• Integrate and evaluate multiple commercial and open-source LLMs, including OpenAI, Anthropic, Llama, and Mistral, based on application, performance, and cost requirements.
• Develop scalable and high-performance backend services and APIs using Python, FastAPI, and asynchronous programming.
• Fine-tune and customize LLMs for domain-specific use cases using PyTorch, TensorFlow, Hugging Face, LoRA, and QLoRA.
• Apply advanced prompt engineering techniques to improve LLM response quality and application performance.
• Optimize GenAI workflows for latency, cost, scalability, and reliability.
• Implement monitoring and observability for LLM applications using tools such as LangSmith and Langfuse.
• Containerize AI applications and services using Docker and support production deployments through CI/CD pipelines.
• Deploy and maintain GenAI solutions across cloud environments such as AWS, Azure, or GCP.
• Collaborate with engineering, AI/ML, architecture, and product teams to convert business requirements into scalable AI solutions.
• Troubleshoot and optimize production AI applications, APIs, retrieval pipelines, and model integrations.
• Compensation, Benefits and Duration
• Minimum Compensation: 155,000 USD
• Maximum Compensation: 217,000 USD
• Compensation is based on actual experience and qualifications of the candidate. The above is a reasonable and a good faith estimate for the role.
• Medical, vision, and dental benefits, 401k retirement plan, variable pay/incentives, paid time off, and paid holidays are available for full-time employees.
• This position is not available for independent contractors
• No applications will be considered if received more than 120 days after the date of this post.