Job Title: SR GEN AI Engineer
Location: Chicago ,IL
Duration: 12 Months + Extension
Bill Rate: $87/hour
Job Type: W-2 Contract
Client: To Be Discussed Later
Work Authorization: US-Citizen, H-1B, OPT-EAD, GC-EAD
POSITION OVERVIEW :
Job Description
We are looking for an experienced Software Engineer with strong expertise in Machine Learning, Large Language Models (LLMs), and AI infrastructure. The candidate will be responsible for designing, developing, deploying, and optimizing production-grade LLM inference services that power Generative AI applications.
The ideal candidate should have hands-on experience in model serving, inference optimization, GPU computing, and scalable Kubernetes-based infrastructure.
Key Responsibilities
- Design, develop, deploy, and maintain scalable LLM inference services.
- Optimize model serving performance, latency, throughput, and infrastructure costs.
- Work on inference optimization techniques such as Quantization (INT8/INT4, FP8, AWQ, GPTQ), KV-cache management, Paged Attention, and Prefix Caching.
- Implement and optimize model serving using TensorRT-LLM, vLLM, SGLang, or Triton Inference Server.
- Work with PyTorch and the Hugging Face ecosystem.
- Deploy and manage AI workloads using Kubernetes, Docker, and GPU scheduling.
- Build integrations with external LLM APIs and internal orchestration frameworks.
- Implement monitoring, logging, tracing, and observability using Prometheus, Grafana, Splunk, Datadog, or OpenTelemetry.
- Develop model evaluation and regression testing pipelines.
- Work with RAG pipelines and vector databases.
- Perform GPU workload cost optimization and capacity planning.
- Maintain CI/CD pipelines and Infrastructure as Code.
- Prepare technical documentation, design documents, and benchmark reports.
Required Skills
- 5+ years of overall Software Engineering experience.
- Minimum 2+ years of hands-on experience working with ML/LLM systems in production.
- Strong programming skills in Python.
- Working knowledge of Go, C++, or Rust.
- Experience with TensorRT-LLM, vLLM, SGLang, or Triton Inference Server.
- Strong understanding of LLM inference optimization and GPU performance tuning.
- Experience with PyTorch and Hugging Face.
- Hands-on experience with Kubernetes, Docker, and NVIDIA GPU infrastructure.
- Knowledge of REST APIs, gRPC, and distributed systems.
- Experience with model evaluation, performance profiling, and benchmarking.
- Understanding of CI/CD and Infrastructure as Code tools such as Terraform and Helm.
Equal Opportunity Employer: We are an equal opportunity employer. All aspects of employment including the decision to hire, promote, discipline, or discharge, will be based on merit, competence, performance, and business needs. We do not discriminate on the basis of race, color, religion, marital status, age, national origin, ancestry, physical or mental disability, medical condition, pregnancy, genetic information, gender, sexual orientation, gender identity or expression, national origin, citizenship/ immigration status, veteran status, or any other status protected under federal, state, or local law.
