SRE - AI ML Support Engineer

Experience: 6+ years

NP-0 to 30 days

Please find JD:

We are hiring a “SRE [Site Reliability Engineer] AI ML Support” engineer for our “Enterprise-grade highperformance supercomputing” platform. We are helping enterprises and service providers build their AI 

inference platforms for end users, powered by our state-of-the-art RDU (Reconfigurable Dataflow Unit) 

hardware architecture. Our cloud-agnostic, enterprise-grade MLOps platform abstracts infrastructure 

complexity and enables seamless deployment, management, and scaling of foundation model workloads at 

production scale. You’ll contribute to the core of our enterprise-grade AI platform, collaborating across teams to 

ensure our systems are performant, secure, and built to last. This is a high-impact, high-visibility role working 

at the intersection of AI infrastructure, enterprise software, and developer experience.

Minimum Requirements:

• Foundational ML knowledge with hands-on experience working with machine learning models, 

especially large language models (LLMs) and LLM APIs

• Strong programming skills in Python, including working with ML frameworks (PyTorch, Huggingface, 

LangChain, etc) as well as building scripts, automation

• Solid understanding of Generative AI concepts (such as RAG) and applied use cases 

• Exposure to Linux systems and familiarity with troubleshooting environment/setup issues

• Ability to investigate, triage, and resolve customer or internal issues related to ML workflows, APIs, and 

AI-based applications

• Experience with issue tracking, documentation, and collaboration platforms (e.g., ticketing systems, 

project tracking tools, knowledge bases)

• Proficiency with Docker for containerization and shell scripting for system automation

• Good communication and collaboration skills to work with cross-functional teams as well as external 

customers or stakeholders

Nice to have:

• Familiarity with multi-modal models (e.g. Llama 4 Maverick)

• Familiarity with ML Ops practices – monitoring, observability, exposure to related libraries and 

frameworks like OpenSearch, Prometheus and Grafana

• Strong hands-on exposure to Linux system administration and network administration, including 

troubleshooting, system monitoring, and optimizing performance

• Experience working with Kubernetes (on-prem deployments preferred) for managing containerized ML 

workloads

• Exposure to one or more public cloud platforms (AWS, GCP, Azure, etc)

• Strong customer-facing communication skills to handle escalations, reliability concerns, and solution 

discussions with stakeholders and clients in a B2B environment

Ways to stand out from the crowd:

• Prior experience working with APIs and SDKs of major LLM providers (OpenAI, Anthropic, Hugging 

Face, etc)

• Demonstrated ability to resolve complex issues in production ML systems 

• Knowledge of fine-tuning, prompt engineering, and optimizing LLM usage in production.

Thanks

Aparna Surnis