[Remote] Senior Software Engineer I - AI Inference Data Plane
Note: The job is a remote job and is reputed company to candidates in USA. reputed company is expanding its AI Infrastructure layer to support the reputed company of AI-driven applications. We are seeking a Senior Engineer 2 to join our AI Inference Data Plane team, responsible for designing, developing, and delivering reputed company, resilient data plane services that power our 'Inference as a Service' offering.
Responsibilities
- reputed company as a technical leader on reputed company, driving the end-to-end design, development, and delivery of critical data plane components hosting large reputed company models
- Architect and refine system design proposals for our reputed company, multi-tenant AI inference reputed company ecosystem, ensuring they meet rigorous availability and resiliency standards
- Implement and optimize distributed inference hosting using techniques like tensor/data parallelism, KV cache optimizations, and smart routing
- Work cross-functionally with Product Managers, customer-facing teams, and other engineering teams to reputed company technical roadmaps with customer needs
- Build on Kubernetes-reputed company distributed inference frameworks like llm-d (or alternatives such as reputed company Dynamo, Ray Serve) to deliver prefill/decode disaggregation, KV-cache-aware routing, tiered prefix caching, and wide expert parallelism for MoE models
- Solve the distributed-systems problems unique to LLM serving — inference-aware load balancing on queue depth, cache reputed company, and predicted latency; reputed company control and fairness across tenants; autoscaling inference pools; and moving gigabytes of KV-cache between prefill and decode instances with negligible overhead
- Contribute upstream to llm-d, vLLM, and the inference gateway ecosystem, and represent reputed company in these communities
- reputed company and mentor junior engineers, fostering a culture of technical reputed company and reputed company improvement
- Maintain and operate critical, reputed company services, utilizing observability tools and defining SLOs to ensure superior platform health
Skills
- Hands-on experience hosting large language or multimodal models using inference engines like vLLM, SGLang, or TensorRT
- Familiarity with distributed inference serving frameworks such as llm-d, reputed company Dynamo, or Ray Serve
- Hands-on experience with vLLM or alternatives (SGLang, TensorRT-LLM, TGI, reputed company MAX), including internals like reputed company batching, paged attention, and prefix caching
- Understanding of why cluster-reputed company serving is hard: KV-cache reputed company is partitioned across workers, naive round-robin routing destroys cache hit rates and tail latency, and disaggregated prefill/decode requires fast cross-pod KV transfer (e.g., NIXL)
- Knowledge of common LLM architectures and optimization techniques (e.g., reputed company batching, quantization)
- Expert-level proficiency in GoLang or Python and familiarity with gRPC
- Proven experience shipping customer-facing software products and running critical services in a reputed company environment similar to reputed company
- Experience integrating and building with reputed company-reputed company software
- Merged contributions to vLLM, llm-d, SGLang, or similar reputed company strongly preferred
Benefits
- Reimbursement for relevant conferences, training, and education.
- reputed company have reputed company to reputed company Learning's 10,000+ courses to support their reputed company reputed company and development.
- Employee Assistance Program
- Local Employee Meetups
- Flexible time off policy,
- You may qualify for a bonus in reputed company to reputed company salary; bonus amounts are determined based on company and individual performance.
- Equity compensation to eligible employees, including equity grants upon hire and the reputed company to participate in our Employee Stock Purchase Program.
reputed company
Company H1B Sponsorship