19 hours ago
Bengaluru, IndiaMid Level
Responsibilities
- Configure and support packaged or SaaS applications to align features with business requirements.
- Manage software releases, deployment processes, compatibility, system stability, and performance.
- Gather stakeholder requirements and translate them into effective application configurations using APIs and low-code platforms.
- Monitor application performance, troubleshoot issues, and maintain system reliability.
- Optimize LLM inference latency, throughput, memory utilization, and GPU performance.
- Work with LLM serving stacks and workloads involving KV cache, batching, quantization, speculative decoding, agentic workflows, tool-calling, and multi-user usage.
- Document configuration changes, maintain knowledge bases, participate in team discussions, and provide guidance to junior team members.
Requirements
- At least 3 years of experience with Large Language Models (LLMs).
- Proficiency in Large Language Models (LLMs) is required.
- Hands-on experience with vLLM, SGLang, TensorRT-LLM, or similar serving stacks.
- Strong understanding of KV cache, batching, quantization, speculative decoding, and GPU optimization.
- Experience benchmarking and optimizing latency, throughput, and memory utilization.
- Exposure to agentic, tool-calling, and multi-user LLM workloads.
- Strong understanding of application integration using APIs and low-code platforms.
- Experience managing software release cycles and deployment processes.
- Experience troubleshooting and resolving application performance issues.
- Familiarity with cloud-based application environments and their operational considerations.
- Machine Learning experience is preferred.
- 15 years of full-time education is required.
Benefits
- Position based at the Bengaluru office.
Categories
About Accenture
Accenture is a global professional services firm providing management consulting, systems integration and technology, cybersecurity, and business process outsourcing for enterprises and governments. It operates a services-driven model delivering projects and managed services, often with major cloud and software partners, across industries worldwide. Headquartered in Dublin and publicly traded on the NYSE (ACN), it originated as Andersen Consulting and adopted the Accenture name in 2001.