Senior LLM Engineer (AI)

Location: Remote

Company

Innovation-driven company building and deploying AI solutions across space, manufacturing, AdTech, and FinTech by combining research with production engineering.

What you will do

• Design and ship agentic AI systems with supervisor, planner, executor, routing, memory, context, tool-calling, and failure-handling patterns.
• Adapt open-source LLMs using fine-tuning or parameter-efficient methods and optimize inference latency and cost for production.
• Implement RAG pipelines including embeddings, retrieval, re-ranking, and grounding.
• Build structured generation, guardrails, post-processing, automated evaluation, regression testing, and prompt/model versioning.
• Deliver containerized services and APIs with CI/CD, observability, SLOs, alerting, and incident readiness.
• Collaborate with product, platform, and data teams to integrate GenAI into workflows and mentor other engineers.

Requirements

• 5+ years building production ML/AI systems, including 2+ years at senior or lead level.
• Strong Python engineering skills covering testing, packaging, code quality, and performance profiling.
• Hands-on experience with LLMs and agentic AI in real systems, including tool calling, orchestration, and workflow integration.
• Experience adapting LLMs with LoRA, QLoRA, PEFT, or equivalent methods, and evaluating quality and safety.
• Experience implementing and operating RAG and retrieval components in production.
• Strong MLOps fundamentals covering containers, CI/CD, model and service versioning, and monitoring.
• API and service development experience with REST or gRPC, authentication, rate limits, error handling, and resilience patterns.
• Ability to operate in AWS, GCP, or Azure cloud environments under production constraints.

Nice to have

• Inference optimization with quantization, batching, caching, and GPU serving using vLLM, TGI, or similar tools.
• Agent safety engineering, including prompt-injection defenses, tool security, sandboxing, and red teaming.
• Advanced evaluation methods such as LLM-as-judge, preference testing, rubric-based grading, and A/B testing.
• Vector database operations, tuning, and retrieval performance engineering.
• Event-driven or workflow orchestration experience with Temporal, Airflow, n8n, or equivalents.
• Multilingual GenAI experience and internationalization practices.

Culture & Benefits

• Remote work arrangement.
• Production-focused work combining state-of-the-art research with robust engineering.