About the Role
We are seeking a highly skilled Python LLM Engineer to join our AI team. The ideal candidate should have deep expertise in large language models (LLMs), experience in building Retrieval-Augmented Generation (RAG) systems, and a strong background in AI-driven applications. This role requires hands-on experience with LangChain, multimodal AI, vector databases, agentic AI, and cloud-based AI infrastructure, particularly AWS and AWS Bedrock. Python will be the primary development language for this role.
Key Responsibilities
- Design, develop, and optimize applications leveraging LLMs using LangChain and other frameworks.
- Build and fine-tune Retrieval-Augmented Generation (RAG) based AI systems for efficient information retrieval.
- Implement and integrate major LLM APIs such as OpenAI, Anthropic, Google Gemini, and Mistral.
- Develop and optimize AI-driven voice applications and conversational agents using Python.
- Research and apply the latest advancements in AI, multimodal models, and vector databases.
- Architect and deploy scalable AI applications using AWS services, including AWS Bedrock.
- Design and implement vector search solutions using Pinecone, Weaviate, FAISS, or similar technologies.
- Develop agentic AI products that leverage autonomous decision-making and multi-agent coordination.
- Write efficient and scalable backend services in Python for AI-powered applications.
- Develop and optimize AI model fine-tuning and inference pipelines in Python.
- Implement end-to-end MLOps pipelines for model training, deployment, and monitoring using Python-based tools.
- Optimize LLM inference for performance and cost efficiency using Python frameworks.
- Ensure the security, scalability, and reliability of AI systems deployed in cloud environments.
Required Skills and Experience
- Strong experience with Large Language Models (LLMs) and their APIs (OpenAI, Anthropic, Cohere, Google Gemini, Mistral, etc.).
- Proficiency in LangChain and experience in developing modular AI pipelines.
- Deep knowledge of Retrieval-Augmented Generation (RAG) and its implementation.
- Experience with voice AI technologies, ASR (Automatic Speech Recognition), and TTS (Text-to-Speech), using Python-based frameworks.
- Familiarity with multimodal AI models (text, image, audio, and video processing) and Python libraries such as OpenCV, PIL, and SpeechRecognition.
- Hands-on experience with vector databases (Pinecone, Weaviate, FAISS, ChromaDB, etc.).
- Strong background in developing agentic AI products and autonomous AI workflows.
- Expertise in Python for AI/ML development, including libraries like TensorFlow, PyTorch, Hugging Face, FastAPI, and LangChain.
- Experience with AWS cloud services, including AWS Bedrock, Lambda, S3, and API Gateway, with Python-based implementations.
- Strong understanding of AI infrastructure, model deployment, and cloud scalability.
Preferred Qualifications
- Experience in reinforcement learning and self-improving AI agents.
- Exposure to prompt engineering, chain-of-thought prompting, and function calling.
- Prior experience in building production-grade AI applications in enterprise environments.
- Familiarity with CI/CD pipelines for AI model deployment and monitoring, using Python-based tools such as DVC, MLflow, and Airflow.