On-Prem LLM Platform Engineer (OpenShift AI GPU)

In the assigned Job Role of Data Science Consultant 1 your Area Of Responsibility will be as below:
Participate in data extraction transformation and preparation.
Resolve common data issues and ensure quality for model development.
Participate in developing models using statistical or machine learning techniques and collaborate with technology teams to operationalize them into analytics tools or scripts.
Participate in model testing and validation selecting the best-performing algorithms based on statistical and business metrics.
Participate in the development of advanced analytics and machine learning or deep learning models including LLMs using predefined processes and tools like SAS and R/ Python.
Participate in defining analytics problems; execute visualization analysis and predictive modeling with senior support.
Identify data sources and extract from RDBMS and develop UI/UX for client usage.
Participate in model performance while making minor adjustments and escalate risks or compliance concerns and generate reports on deviations or schedule slippages.
Proactively participate in detailed documentation of model development testing and deployment activities for reproducibility.
Work closely with business and technology teams to translate requirements into actionable models while communicating results effectively.
Apply predefined quality measurement frameworks if any to individual project tasks.
Participate in deploying analytics tools in test and production environment while ensuring they meet operational requirements.



Your contribution to the team:

Strong analytical and problem-solving mindset with hands-on model development skills.
Ability to translate business needs into actionable analytics solutions.
Focus on data quality validation and performance optimization.
Effective collaboration with business and technology stakeholders.
Commitment to continuous learning knowledge sharing fostering team development.

Benefits

Along with competitive pay as a full-time Infosys employee you are also eligible for the following benefits:

• Medical/Dental/Vision/Life Insurance
• Long-term/Short-term Disability
• Health and Dependent Care Reimbursement Accounts
• Insurance (Accident Critical Illness Hospital Indemnity Legal)
• 401(k) plan and contributions dependent on salary level
• Paid holidays plus Paid Time Off

About Us
Infosys is a global leader in next-generation digital services and consulting. We enable clients in more than 50 countries to navigate their digital transformation. With over four decades of experience in managing the systems and workings of global enterprises we expertly steer our clients through their digital journey. We do it by enabling the enterprise with an AI-powered core that helps prioritize the execution of change. We also empower the business with agile digital at scale to deliver unprecedented levels of performance and customer delight. Our always-on learning agenda drives their continuous improvement through building and transferring digital skills expertise and ideas from our innovation ecosystem.

EEO
Infosys provides equal employment opportunities to applicants and employees without regard to race; color; sex; gender identity; sexual orientation; religious practices and observances; national origin; pregnancy childbirth or related medical conditions; status as a protected veteran or spouse/family member of a protected veteran; or disability.

Required Skill and Experience
Strong hands-on experience with OpenShift (OCP) and OpenShift AI

Deep understanding of Kubernetes cluster operations and model serving

Experience with vLLM Triton TensorRT-LLM or SGLang
Expertise in inference optimization techniques including:

Proficiency in model quantization techniques (FP8 AWQ GPTQ) and performance tuning

Experience with GPU orchestration and scheduling
Working knowledge of CUDA NCCL and MIG concepts
Exposure to NVIDIA H200 GPUs (highly preferred)

Preferred Skill and Experience
Exposure to NVIDIA H200 GPUs (highly preferred)
Deploy and run LLMs on-prem using:
o OpenShift (OCP) OpenShift AI Kubernetes ML serving patterns
o Model serving stacks: vLLM Triton TensorRT-LLM SGLang
Unfold an LLM end-to-end:
o Package model artifacts containerize configure runtime serve endpoints
o Implement authn/authz secrets networking and endpoint routing patterns
GPU-first platform engineering:
o GPU orchestration scheduling resource quotas
o Performance tuning for throughput/latency memory utilization
o Awareness of CUDA/NCCL tensor parallelism MIG concepts

Additional Required Qualifications
Bachelors degree or foreign equivalent required from an accredited institution. Will also consider three years of progressive experience in the specialty in lieu of every year of education.
This position may require relocation and/or travel to work/project location.
Candidates authorized to work for any employer in the United States without employer-based visa sponsorship are welcome to apply. Infosys is unable to provide immigration sponsorship for this role now or in the future.

Overview
The Infosys Data and Analytics (DNA) unit is at the forefront of transforming data into actionable insights driving business growth and operational efficiency. We specialize in leveraging advanced AI and analytics to create innovative solutions that address complex business challenges. Our team is dedicated to pioneering the future of data-driven decision-making enabling organizations to unlock new opportunities and achieve sustainable success. Join us to be part of a dynamic team that is revolutionizing the way businesses harness the power of data and AI. At Infosys DNA youll have the opportunity to work with cutting-edge technologies collaborate with industry experts and contribute to transformative projects that shape the future of business. We are committed to fostering a culture of continuous learning and growth ensuring that our team members thrive in a dynamic and supportive environment. If youre passionate about AI and eager to make a significant impact the Infosys DNA unit is the perfect place for you to grow and excel.