Job Role: LLM Engineer
About Us
At Opkey, we are transforming the ERP testing landscape with our AI-powered solutions, trusted by 250+ global enterprises, including GAP, Pfizer, and KPMG. Our platform accelerates ERP transformation across Oracle Fusion Cloud, SAP S/4HANA, Workday, Salesforce, and other enterprise applications.
Headquartered in Dublin, Californiawith offices in Pittsburgh, New York, Noida, and BangaloreOpkey is a fast-growing, VC-backed SaaS company at the forefront of agentic AI, autonomous testing, and enterprise automation.
About The Role
We're looking for an LLM Engineer who is passionate about building production-grade GenAI systems. This role is ideal for someone who enjoys experimenting with language models, optimizing model performance, and integrating LLM capabilities into enterprise SaaS products.
What We're Looking For
- Bachelors with 2-4 years, or Master's with 1-2 years, of experience in AI/ML engineering with hands-on exposure to NLP or GenAI.
- Strong understanding of LLMs, embeddings, transformers, and generative AI concepts.
- Experience with LLM fine-tuning (LoRA, QLoRA, PEFT) or training SLMs for domain-specific tasks.
- Practical experience with frameworks such as PyTorch, JAX, Hugging Face Transformers.
- Hands-on experience implementing RAG pipelines and working with vector databases (e.g., Pinecone, Weaviate, FAISS).
- Strong Python programming skills with experience in building APIs or backend services.
- Knowledge of deploying AI models to cloud platforms (AWS, E2E, RunPod).
- Basic understanding of the MLOps lifecyclemodel packaging, containerization (Docker), Evaluation, Monitoring, etc.
What You'll Do
- Build, fine-tune, and deploy Large Language Models (LLMs) and Small Language Models (SLMs) for product use cases.
- Develop Retrieval-Augmented Generation (RAG) architectures, vector-search workflows, and intelligent document-processing pipelines.
- Optimize model latency, accuracy, token efficiency, and cost for production environments.
- Implement scalable MLOps workflows, including CI/CD pipelines, model versioning, monitoring, and automated evaluation.
- Experiment with prompting, fine-tuning, quantization, distillation, and domain adaptation for ERP/testing-specific use cases.
- Work with vector databases (Pinecone, FAISS, Milvus, etc.) to build robust retrieval systems.
- Research new GenAI techniques and contribute to innovation across Opkey's AI roadmap.
Bonus Points If You Have
- Experience training or fine-tuning an SLM / domain-specific language model (pre-training or domain-adapted fine-tuning).
- Exposure to ERP, enterprise workflows, or automation/testing domains.
- Contributions to open-source AI/ML projects.
- Experience optimizing model inference (quantization, caching, batching).
- Publications, blogs, or research in NLP or GenAI.
Why You'll Love Working Here
- Work on cutting-edge agentic AI and LLM engineering solutions, which will power the future of enterprise automation.
- Build AI features used globally by Fortune 500 enterprises.
- Collaborative, learning-driven culture with opportunities to explore and innovate.
- Fast-growing startup environment with high ownership and end-to-end impact.
- Flexible work culture, global exposure, and growth-driven leadership.
Skills: erp,slm,automation,aws,llm,genai,ai/ml,nlp,pytorch,python
