LLM Engineer

Opkey is seeking a motivated LLM Engineer to join our dynamic team in Noida, India. This role is perfect for an individual passionate about developing production-grade Generative AI (GenAI) systems. You will have the opportunity to experiment with language models, enhance their performance, and integrate cutting-edge LLM capabilities into our enterprise SaaS products.

What We're Looking For:

• Bachelors degree with 2-4 years of experience, or Masters degree with 1-2 years of experience in AI/ML engineering, with practical exposure to Natural Language Processing (NLP) or GenAI.
• A solid understanding of Large Language Models (LLMs), embeddings, transformers, and core GenAI concepts.
• Proven experience in LLM fine-tuning techniques like LoRA, QLoRA, or PEFT, or in training Small Language Models (SLMs) for specialized tasks.
• Hands-on experience with ML frameworks such as PyTorch, JAX, and Hugging Face Transformers.
• Demonstrated ability to implement Retrieval-Augmented Generation (RAG) pipelines and work with vector databases like Pinecone, Weaviate, or FAISS.
• Proficiency in Python programming, with experience in building APIs or backend services.
• Knowledge of deploying AI models to cloud platforms, including AWS, E2E, and RunPod.
• Familiarity with the MLOps lifecycle, encompassing model packaging, containerization (Docker), evaluation, and monitoring.

What You'll Do:

• Develop, fine-tune, and deploy LLMs and SLMs for various product applications.
• Design and implement RAG architectures, vector search workflows, and intelligent document processing pipelines.
• Optimize LLM performance in production environments, focusing on latency, accuracy, token efficiency, and cost.
• Build and maintain scalable MLOps workflows, including CI/CD, model versioning, monitoring, and automated evaluation.
• Experiment with advanced techniques such as prompting, fine-tuning, quantization, distillation, and domain adaptation, particularly for ERP and testing use cases.
• Utilize vector databases (e.g., Pinecone, FAISS, Milvus) to construct robust retrieval systems.
• Stay abreast of the latest GenAI advancements and contribute to Opkey's AI roadmap through research and innovation.

Bonus Points If You Have:

• Experience training or fine-tuning SLMs or domain-specific language models.
• Familiarity with ERP systems, enterprise workflows, or automation/testing domains.
• Contributions to open-source AI/ML projects.
• Experience in optimizing model inference (quantization, caching, batching).
• Published work, blogs, or research in NLP or GenAI.

Join Opkey to work on cutting-edge agentic AI and LLM engineering solutions that will shape the future of enterprise automation. You'll build AI features used by Fortune 500 companies globally, contributing to a collaborative and learning-driven culture in a fast-paced startup environment that offers high ownership and end-to-end impact, along with flexible work arrangements and global exposure.