On-Premise AI Infrastructure & LLM Serving Consultant / Engineer (Part-Time / Contract)

Company Description Molecular Connections (MC) is a data and AI-driven solutions provider with over two decades of experience in Big Data and Data Science, helping customers achieve digital transformation through proprietary AI-powered models. The organization leverages AI, machine learning, and linked data technologies to improve efficiency across multiple verticals and create new revenue streams for global clients. MC delivers end-to-end software development and data insights for leading pharma and STEM industries, enabling advanced content engineering and analytics across diverse domains. The company has a strong focus on innovation and inclusion and is ranked among the top 15 best companies for women to work for in India. MC’s group also includes Molecular Connections Analytics Pvt. Ltd. and Molecular Connections Research Pvt. Ltd., expanding its reach in analytics and research services.

Role Description The On-Premise AI Infrastructure & LLM Serving Consultant / Engineer is a part-time, contract role focused on designing, deploying, and maintaining secure on-premise AI infrastructure and large language model (LLM) serving environments. The consultant / engineer will work in a hybrid arrangement based in the Greater Bengaluru Area, with a mix of on-site collaboration and work-from-home flexibility, while aligning with project and stakeholder needs. Day-to-day responsibilities include assessing existing infrastructure, setting up GPU/CPU clusters, configuring containerization and orchestration tools, and optimizing resource utilization for AI workloads. The role involves implementing and maintaining LLM serving stacks, integrating models with internal applications, ensuring robust monitoring, logging, and security controls, and troubleshooting performance and reliability issues. The consultant / engineer will collaborate with data science, product, and DevOps teams to define requirements, document best practices, and support scalable, compliant AI and data solutions for MC’s customers.

Qualifications

• Infrastructure and systems skills: Experience with Linux administration, networking fundamentals, storage management, and setting up on-premise compute (including GPU/CPU clusters) for AI workloads.
• Containerization and orchestration skills: Proficiency with Docker or similar container technologies, and Kubernetes or equivalent orchestration platforms for deploying and managing AI services.
• AI/ML and LLM serving skills: Hands-on experience with machine learning workflows, LLM frameworks or serving tools (e.g., model inference servers, vector databases, model gateways), and optimizing performance and scalability.
• DevOps and automation skills: Familiarity with CI/CD pipelines, configuration management, and infrastructure-as-code tools to automate builds, deployments, and environment provisioning.
• Security, monitoring, and reliability skills: Knowledge of access control, encryption, compliance-aware design, and use of monitoring, logging, and alerting tools to maintain reliable AI infrastructure.
• Collaboration and communication: Ability to work closely with cross-functional teams, clearly document