P
Senior LLM Platform Engineer
Sin especificarTiempo completoAI EngineeringTelecommunications
Own the architecture, delivery, and operation of a secure local large-language-model platform for internal teams. Build practical generative AI capabilities that protect proprietary data and provide reliable, measurable results.
Responsabilidades
- Own the architecture and technical roadmap for a secure, reliable local LLM platform.
- Partner with internal teams to prioritize use cases and define measurable requirements.
- Build a modular model-inference gateway with stable APIs, model routing, streaming, and capacity controls.
- Evaluate and optimize open-weight models and serving across available compute resources.
- Design and operate search and RAG pipelines, including ingestion, retrieval, ranking, citations, freshness, and deletion.
- Enforce source permissions and integrate identity, access controls, secrets management, and audit logging.
- Create evaluation datasets, automated assessments, release gates, and regression tests for models and platform changes.
- Establish observability for model workflows, service health, performance, and user feedback.
- Develop safe tool-calling workflows with least-privilege access, sandboxing, validation, and human approval where needed.
- Integrate the platform with developer tools, source control, CI workflows, knowledge systems, and internal applications.
- Build production operations, including deployment, backups, disaster recovery, capacity planning, security updates, and incident response.
- Protect sensitive information and mitigate prompt injection, data poisoning, unsafe outputs, and model-supply-chain risks.
- Assess when fine-tuning or other model adaptation is justified by measured results.
- Improve adoption through documentation, examples, training, and collaboration with internal teams.
Requisitos
- BSc or MSc in Computer Science, Computer Engineering, Electrical Engineering, Data Science, or a related field, or equivalent practical experience.
- Typically 7+ years of experience in production software, ML platform, search, data, or infrastructure engineering, including recent experience delivering LLM-powered systems.
- Strong Python skills and experience designing APIs, services, libraries, and data pipelines.
- Understanding of transformer models and production inference, including batching, caching, quantization, context management, and tool calling.
- Experience building production retrieval-augmented generation or enterprise-search systems and evaluating retrieval quality.
- Experience deploying containerized Linux services using Docker and Kubernetes or equivalent orchestration.
- Practical experience with GPU-backed serving, performance profiling, capacity planning, monitoring, and reliability.
- Knowledge of distributed systems, authentication, authorization, API security, encryption, audit logging, and data lifecycle controls.
- Experience with Git, automated testing, CI/CD, infrastructure as code, observability, and production incident response.
- Ability to lead cross-functional technical work and communicate complex AI behavior clearly.
Se valora
- Experience with on-premises, private-cloud, restricted-network, or air-gapped LLM deployments.
- Familiarity with model-serving systems, GPU optimization, vector databases, hybrid search, and LLM evaluation or tracing tools.
- Experience with parameter-efficient fine-tuning, code intelligence, developer tools, enterprise identity, AI governance, or LLM red-teaming.
- Knowledge of telecommunications, RAN/Open RAN, or cloud-native network functions.
- Contributions to open-source AI, search, MLOps, or infrastructure projects.