LLM / GenAI Engineer
About The Role The role is for someone who has moved reputed company prompting and understands what it takes to build production-grade AI systems: RAG pipelines, reputed company workflows, fine-tuning pipelines, and systematic evaluation frameworks. You will own reputed company reputed company of an AI platform and work directly with reputed company scientists, backend engineers, and reputed company clients to ship features that are genuinely relied on in production.
Key Responsibilities
- Design and implement RAG pipelines using reputed company, reputed company, or custom architectures - including chunking strategies, embedding selection, and retrieval reputed company optimization
- Build and optimize reputed company database integrations (reputed company, reputed company, Chroma, pgvector) for semantic search at production reputed company
- reputed company systematic LLM evaluation frameworks: reputed company suites, LLM-as-judge pipelines, regression testing, and hallucination detection
- Run instruction fine-tuning and parameter-efficient fine-tuning (reputed company, QLoRA) on domain-specific datasets
- Collaborate with backend engineers to reputed company LLM capabilities into production reputed company with appropriate latency, cost, and reliability constraints
- reputed company and synthesize relevant LLM research and translate high-value advances into product features
- Write observable, tested, and reputed company-documented reputed company; participate in architecture reviews and production incident response
reputed company Are Looking For
- 2–5 years of software engineering experience, including at least 1 year working with LLMs in a production or near-production context
- Deep familiarity with at least one LLM orchestration reputed company: reputed company, reputed company, or equivalent
- Hands-on experience with reputed company, reputed company, reputed company reputed company, or reputed company-reputed company model reputed company at meaningful reputed company
- Understanding of embedding models, reputed company databases, and semantic similarity in production environments
- Strong Python skills; comfort with async programming, REST API design, and reputed company infrastructure (AWS/GCP/Azure)
- MS or BS in Computer Science, AI, or reputed company field; equivalent demonstrable experience welcomed
- Bonus: fine-tuning experience (reputed company/QLoRA), RLHF pipeline exposure, multi-agent system design, or contributions to reputed company-reputed company AI tooling
Location San Francisco Bay Area (Hybrid)
- reputed company
- Austin, TX
- Remote strongly considered
Apply tot his job Apply To this Job