LLM Engineer

About Us

At Opkey , we are transforming the ERP testing landscape with o ur AI-powered No-Code Test Automation Platform, 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, California with offices in Pittsburgh, New York, Noida, and Bangalore Opkey 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

1. Bachelors with 2- 4 years , or Masters with 1-2 years, of experience in AI/ML engineering with hands-on exposure to NLP or GenAI .


2. Strong understanding of LLMs, embeddings , transformers, and generative AI concepts.


3. Experience with LLM fine-tuning ( LoRA , QLoRA , PEFT) or training SLMs for domain-specific tasks.


4. Practical experience with frameworks such as PyTorch , JAX , Hugging Face Transformers .


5. Hands-on experience implementing RAG pipelines and working with vector databases (e.g., Pinecone, Weaviate , FAISS).


6. Strong Python programming skills with experience in building APIs or backend services.


7. Knowledge of deploying AI models to cloud platforms (AWS, E2E , RunPod ).


8. Basic u nderstanding of MLOps lifecycle model packaging, containerization ( Docker ), Evaluation , M onitoring, etc.

What You ll Do

1. Build, fine-tune, and deploy Large Language Models (LLMs) and Small Language Models (SLMs) for product use cases.


2. Develop Retrieval-Augmented Generation (RAG) architectures, vector-search workflows, and intelligent document-processing pipelines.


3. Optimize model latency, accuracy, token efficiency, and cost for production environments.


4. Implement scalable MLOps workflows including CI/CD pipelines, model versioning, monitoring, and automated evaluation.


5. Experiment with prompting, fine-tuning, quantization, distillation, and domain adaptation for ERP/testing-specific use cases.


6. Work with vector databases (Pinecone, FAISS, Milvus , etc.) to build robust retrieval systems


7. Research new GenAI techniques and contribute to innovation across Opkey s AI roadmap.

Bonus Points If You Have