Job
Description
We are seeking a proficient AI/ML Engineer responsible for testing, deploying, and hosting various Large Language Models (LLMs). The role involves monitoring deployed agentic services, ensuring their optimal performance, and staying abreast of the latest advancements in AI technologies. Key Responsibilities: LLM Deployment & Hosting Evaluate, test, and deploy diverse LLMs on cloud-based and on-premise infrastructures. Optimize model performance for scalability and efficiency. Implement secure API endpoints and model-serving pipelines. Strong CI/CD skills and knowledge of CI/CD tools like Jenkins, GitHub Actions, CircleCI etc. Agentic AI Services Deploy and maintain AI agents using frameworks such as CrewAI, Agnos(Phi Data), AutoGen etc. Integrate LLMs into business workflows and automation tools. Design, monitor, and enhance agentic services for real-world applications. Monitoring & Optimization Utilize advanced observability tools to monitor model performance, latency, and cost efficiency. Implement tools like AgentOps, OpenLIT, Langfuse, and Langtrace for comprehensive monitoring and debugging of LLM applications. Develop logging, tracing, and alerting systems for deployed models and AI agents. Conduct A/B testing and gather user feedback to refine AI behavior. Address model drift and retrain models as necessary. Best Practices & Research Stay updated with the latest advancements in AI, LLMs, and agentic systems. Implement best practices for prompt engineering, reinforcement learning from human feedback (RLHF), and fine-tuning methodologies. Optimize compute costs and infrastructure usage for AI applications. Collaborate with researchers and ML engineers to integrate state-of-the-art AI techniques. Strong knowledge on version control tools like GitHub Qualifications & Skills: Proficiency with LLM frameworks such as Hugging Face Transformers, OpenAI API, or Meta AI models. Strong programming skills in Python and experience with deep learning libraries (PyTorch, TensorFlow, JAX). Experience with cloud platforms (AWS, Azure, GCP) and model deployment tools (Docker, Kubernetes, FastAPI, Ray Serve). Familiarity with vector databases (FAISS, Pinecone, Weaviate) and retrieval-augmented generation (RAG) techniques. Hands-on experience with monitoring tools such as AgentOps, OpenLIT, Langfuse, and Langtrace. Understanding of prompt engineering, LLM fine-tuning, and agent-based automation. Excellent problem-solving skills and the ability to work in a dynamic AI research and deployment team. Preferred Qualifications: Experience in reinforcement learning, fine-tuning LLMs, or training custom models. Knowledge of security best practices for AI applications. Contributions to open-source AI/ML projects or research publications in the field.
