Overview:
Our Technology teams challenge the status quo and reimagine capabilities across industries. Whether through research and development, technology innovation or solution engineering, our team members play a vital role in connecting consumers with the products and platforms of tomorrow.
Responsibilities:
Candidates must be willing to participate in at least one in-person interview, which may include a live whiteboarding or technical assessment session.
As a Senior Software Engineer with an AI focus, you will bridge the gap between experimental machine learning and production-grade software. You won't just be "using" APIs; you will be architecting the systems that orchestrate Large Language Models (LLMs), managing vector data, and building "agentic" workflows that solve real-world business problems. We are looking for a Sr. AI Engineer to architect and champion our "Self-Healing" infrastructure. This role is pivotal in moving our operations beyond traditional threshold-based monitoring and into the era of Observability and Predictive Intelligence
This role also involves providing enterprise-level assistance to our customers and monitoring applications deployed in AWS cloud environments. You will diagnose and troubleshoot issues related to order provisioning and device & SIM activations, utilizing email and chat applications to provide quick answers and resolution for clients' IT issues.
Key Responsibilities:
* AI Orchestration & Integration: Design and implement complex AI workflows using frameworks like LangChain, LlamaIndex, or Haystack
* Production-Grade Development: Write clean, maintainable, and efficient code in Python or Java to support high-traffic applications
* RAG Architecture: Build and optimize Retrieval-Augmented Generation (RAG) pipelines, ensuring high-quality data retrieval from vector databases (Milvus)
* Model Fine-Tuning & Evaluation: Lead the process of fine-tuning open-source models (Llama 3, Mistral) and establishing rigorous evaluation frameworks to measure model accuracy and "hallucination" rates
* System Architecture: Design microservices that handle asynchronous AI processing, caching strategies for LLM responses, and cost-optimization for API tokens
* Mentorship & Leadership: Conduct code reviews, define AI engineering best practices, and mentor junior engineers in the transition to AI-native development
* Intelligent Observability: Design and maintain full-stack observability using Dynatrace and AWS CloudWatch, focusing on the "Boost Mobile" order journey
* Autonomous Remediation: Develop and deploy "Runbooks-as-Code" using Python and Ansible to automate the resolution of recurring Tier-1 and Tier-2 incidents
Qualifications:
Education and Experience:
* Bachelor's Degree in Computer Science, Information Technology or relevant field or 5+ years software engineering experience
* Contributions to open-source AI projects or a portfolio of "Agentic" AI applications
* Certifications in Cloud AI (e.g., AWS Certified Machine Learning - Specialty)
* 5+ years of professional experience in backend or full-stack software development; expert proficiency in Python (the industry standard for AI)
* Deep understanding of Transformer architectures, prompt engineering, and the current LLM landscape (OpenAI, Gemini, and Open Source). 2+ years experience in AI powered development using tools like Kiro
Skills and Qualifications:
* Experience managing Vector Databases and designing ETL pipelines for unstructured data (PDFs, Logs, Documentation)
* Mastery of RESTful and GraphQL API design to expose AI capabilities to frontend applications or third-party services
* Familiarity with AI-specific monitoring tools (Weights & Biases, Arize, or LangSmith) to track model performance in production
* Proficiency in Dynatrace(Grail, Davis AI) or similar
* Hands-on experience with modern AWS/GCP services (Serverless, Kubernetes, EC2)
* High proficiency in Python or Java for API orchestration and custom tool development. Hands-on experience with Bash scripting
* Understanding of vector databases, LLM integration (RAG), and basic data science concepts for tuning anomaly detection models
* Strong ability to diagnose, troubleshoot, and resolve technical issues across computer systems and other technology products
* Excellent problem-solving skills with the ability to provide clear, step-by-step technical guidance both verbally and in writing
* Solid understanding of cloud infrastructure, particularly AWS, and container orchestration using Kubernetes
* Demonstrated fearlessness and curiosity to learn new technologies and tackle complex technical challenges
* Background in software development, with knowledge of modern programming languages, design principles, and coding best practices
* Proficiency in reading, writing, and debugging code across multiple programming languages to support troubleshooting and automation efforts
Visa sponsorship not available for this role
Share this job:
Share this Job