About The Role
The LLM / GenAI Engineer will design, build, and operate production AI systems that combine foundation models, retrieval, structured data, and application logic. The role spans RAG pipelines, tool-using agents, model adaptation, prompt and context strategies, and evaluation infrastructure running on cloud platforms.
The team needs an engineer who can turn research-grade capabilities into reliable products with measurable quality, predictable latency, and strong safeguards. This role works closely with applied scientists, platform engineers, and product teams to ship AI features used in real customer workflows.
Key Responsibilities
- Design and implement production RAG and agentic workflows using Python, LangChain, LlamaIndex, or custom orchestration services
- Build ingestion, chunking, embedding, retrieval, reranking, and citation pipelines backed by vector stores such as Pinecone, Weaviate, Elasticsearch, or pgvector
- Develop LLM evaluation systems covering offline benchmarks, task-specific quality metrics, LLM-as-judge workflows, regression tests, and human review
- Fine-tune and optimize open-source or hosted models using supervised fine-tuning, LoRA, QLoRA, quantization, and inference parameter tuning
- Deploy and operate model-serving services on AWS, GCP, or Azure using Docker, Kubernetes, CI/CD, and observability tools for latency, cost, quality, and failures
- Implement guardrails for prompt injection, sensitive-data exposure, unsafe outputs, hallucinations, and tool-use failures
- Collaborate in architecture reviews and code reviews while producing tested, documented, and maintainable systems that can scale with product demand
What We Are Looking For
- 3–8 years of software engineering, machine learning engineering, or applied research experience, including at least 1 year delivering LLM or GenAI systems to production
- Strong Python skills with experience building APIs, asynchronous services, data pipelines, and production software; familiarity with FastAPI is valuable
- Hands-on experience with transformer-based models, embeddings, tokenization, context windows, prompt design, retrieval, and model evaluation
- Experience with at least one LLM framework such as LangChain, LlamaIndex, Semantic Kernel, DSPy, or an equivalent custom orchestration stack
- Working knowledge of vector databases and search infrastructure, including Pinecone, Weaviate, Milvus, Elasticsearch, OpenSearch, or pgvector
- Experience deploying AI workloads in cloud environments with Docker, Kubernetes, monitoring, logging, and automated testing; familiarity with AWS Bedrock, Vertex AI, or Azure OpenAI is a plus
- Bachelor’s or master’s degree in computer science, machine learning, artificial intelligence, electrical engineering, or a related technical field; Bonus: experience with distributed inference, vLLM or Triton, multimodal models, knowledge graphs, privacy-preserving ML, or responsible AI evaluations