Summary Gainwell is seeking LLM Ops Engineers and ML Ops Engineers to join our growing AI/ML team. This role is responsible for developing, deploying, and maintaining scalable infrastructure and pipelines for Machine Learning (ML) models and Large Language Models (LLMs). You will play a critical role in ensuring smooth model lifecycle management, performance monitoring, version control, and compliance while collaborating closely with Data Scientists, DevOps, and Role Description : Core LLM Ops Responsibilities: - Develop and manage scalable deployment strategies specifically tailored for LLMs (GPT, Llama, Claude, etc.). - Optimize LLM inference performance, including model parallelization, quantization, pruning, and fine:tuning pipelines. - Integrate prompt management, version control, and retrieval:augmented generation (RAG) pipelines. - Manage vector databases, embedding stores, and document stores used in conjunction with LLMs. - Monitor hallucination rates, token usage, and overall cost optimization for LLM APIs or on:prem deployments. - Continuously monitor models for its performance and ensure alert system in place. - Ensure compliance with ethical AI practices, privacy regulations, and responsible AI guidelines in LLM workflows. Core ML Ops Responsibilities: - Design, build, and maintain robust CI/CD pipelines for ML model training, validation, deployment, and monitoring. - Implement version control, model registry, and reproducibility strategies for ML models. - Automate data ingestion, feature engineering, and model retraining workflows. - Monitor model performance, drift, and ensure proper alerting systems are in place. - Implement security, compliance, and governance protocols for model deployment. - Collaborate with Data Scientists to streamline model development and experimentation. - Leadership Skills : Should be able to work as a team lead, interface with team leads of other functions/departments, understand business requirements, cost sensitivity and translate the same to an appropriate solution that is feasible to develop and deploy. What We're Looking For - Bachelors or Masters degree or higher in Computer Science, Data Sciences:Machine Learning, Engineering, or related fields. - Strong experience with ML Ops tools (Kubeflow, ML flow, TFX, Sage Maker, etc.). - Experience with LLM:specific tools and frameworks ( LangChain, Lang Graph, LlamaIndex, Hugging Face, OpenAI APIs, Vector DBs like Pinecone, FAISS, Weavite, Chroma DB etc.). - Solid experience in deploying models in cloud (AWS, Azure, GCP) and on:prem environments. - Proficient in containerization (Docker, Kubernetes) and CI/CD practices. - Familiarity with monitoring tools like Prometheus, Grafana, and ML observability platforms. - Strong coding skills in Python, Bash, and familiarity with infrastructure:as:code tools (Terraform, Helm, etc.).Knowledge of healthcare AI applications and regulatory compliance (HIPAA, CMS) is a plus. - Strong skills in Giskard, Deepeval etc. - Understanding of business use cases, cost sensitivity, strong interpersonal skills, architecting skills and abilities to convince multiple stakeholders. Qualifications - Bachelor or Masters or Higher in Computer Sciences, Data Sciences, or any related field - 7+ years to 10:11 Years of experience in deploying ML/DL and LLM based solutions in large scale deployment environment or related experience - Experience with fine:tuning LLMs and serving them in production at scale. - Knowledge of model compression techniques for LLMs (LoRA, QLoRA, quantization:aware training). - Experience with distributed systems and high:performance computing for large:scale model serving. Awareness of AI fairness, explainability, and governance frameworks. What You Should Expect in This Role - Fully Remote Opportunity : Work from anywhere