Job
Description
We are looking for a skilled Python / AI Engineer with 2 to 5 years of experience to design and build next-generation AI applications using large language models (LLMs), transformer-based architectures, and prompt engineering techniques. The ideal candidate will have hands-on experience with LLMs, open-source models, and Python-based services. ### Roles and Responsibility Design and develop Gen AI applications using LLMs such as OpenAI, Cohere, Claude, etc., and open-source models like LLaMA, Mistral, Falcon. Develop scalable and efficient Python-based services and APIs to serve AI models and workflows. Design prompt templates, chains, and retrieval-augmented generation (RAG) pipelines for AI applications. Integrate vector databases such as FAISS, Pinecone, Weaviate for context-aware responses. Optimize model usage for latency, cost, and accuracy in production environments. Collaborate with product managers, designers, and ML researchers to deliver AI features. Stay current with the Gen AI landscape and evaluate new models and frameworks. ### Job Requirements 2-5 years of experience in Python backend or AI development. Hands-on experience with at least one LLM API or open-source model. Understanding of prompt engineering and RAG pipelines. Experience integrating external tools and APIs with LLM workflows. Proficient in building REST APIs and scalable backend services. Strong debugging, problem-solving, and communication skills. Experience with fine-tuning LLMs or training lightweight transformer models. Exposure to LangChain agents, tool-use, and orchestrators. Working knowledge of cloud-native deployments and containerization. Prior experience building chatbots, copilots, or content generation tools. Strong communication, facilitation, relationship-building, presentation, and negotiation skills. Be highly flexible, adaptable, and creative. Comfortable interacting with senior executives (within the firm and at the client). Strong leadership skills and supervisory responsibility.
