LLM / GenAI Engineer
About The Role
The role is focused on architecting and scaling production-grade generative AI features, moving beyond basic API wrappers to build robust, deterministic systems powered by large language models. The engineer will design orchestration layers, optimize retrieval-augmented generation (RAG) workflows, and implement strict evaluation and guardrail systems to ensure safety, accuracy, and low latency at scale.
The team works at the intersection of modern software engineering and applied AI. This role involves collaborating with backend engineers and product owners to integrate intelligence into core platform workflows, ensuring LLM applications are observable, cost-effective, and highly performant.
Key Responsibilities
• Design and optimize advanced RAG pipelines, utilizing hybrid search, query rewriting, and reranking strategies to maximize retrieval quality.
• Implement systematic LLM evaluation pipelines using frameworks like Ragas, TruLens, or custom LLM-as-a-judge architectures to measure hallucination and accuracy.
• Integrate and manage enterprise-grade vector databases such as Pinecone, Milvus, or pgvector, including indexing strategies and metadata filtering.
• Develop agentic workflows and multi-agent systems using frameworks like LangGraph, Autogen, or custom state machines.
• Deploy, fine-tune, and optimize open-source models (e.g., Llama, Mistral) using LoRA, QLoRA, and quantization techniques for specialized tasks.
• Build robust guardrails and alignment layers using tools like NeMo Guardrails or Llama Guard to ensure safe and deterministic model behavior.
• Monitor LLM latency, cost, and token usage in production using tracing tools such as LangSmith, Phoenix, or Arize.
What We Are Looking For
• 3-6 years of professional software engineering experience, with at least 1.5 years dedicated to building and deploying LLM applications in production.
• Deep proficiency in Python and familiarity with asynchronous programming, FastAPI, and containerization via Docker.
• Hands-on experience with LLM orchestration frameworks like LangChain, LlamaIndex, or DSPy.
• Strong understanding of modern NLP techniques, embedding models, vector spaces, and semantic search.
• Experience deploying production applications on AWS, GCP, or Azure, utilizing managed Kubernetes or serverless containers.
• Bachelor's or Master's degree in Computer Science, Data Science, or a related quantitative technical field.
• Bonus: Experience with vLLM, TensorRT-LLM, custom model hosting, or contribution to open-source GenAI frameworks.
The role is focused on architecting and scaling production-grade generative AI features, moving beyond basic API wrappers to build robust, deterministic systems powered by large language models. The engineer will design orchestration layers, optimize retrieval-augmented generation (RAG) workflows, and implement strict evaluation and guardrail systems to ensure safety, accuracy, and low latency at scale.
The team works at the intersection of modern software engineering and applied AI. This role involves collaborating with backend engineers and product owners to integrate intelligence into core platform workflows, ensuring LLM applications are observable, cost-effective, and highly performant.
Key Responsibilities
• Design and optimize advanced RAG pipelines, utilizing hybrid search, query rewriting, and reranking strategies to maximize retrieval quality.
• Implement systematic LLM evaluation pipelines using frameworks like Ragas, TruLens, or custom LLM-as-a-judge architectures to measure hallucination and accuracy.
• Integrate and manage enterprise-grade vector databases such as Pinecone, Milvus, or pgvector, including indexing strategies and metadata filtering.
• Develop agentic workflows and multi-agent systems using frameworks like LangGraph, Autogen, or custom state machines.
• Deploy, fine-tune, and optimize open-source models (e.g., Llama, Mistral) using LoRA, QLoRA, and quantization techniques for specialized tasks.
• Build robust guardrails and alignment layers using tools like NeMo Guardrails or Llama Guard to ensure safe and deterministic model behavior.
• Monitor LLM latency, cost, and token usage in production using tracing tools such as LangSmith, Phoenix, or Arize.
What We Are Looking For
• 3-6 years of professional software engineering experience, with at least 1.5 years dedicated to building and deploying LLM applications in production.
• Deep proficiency in Python and familiarity with asynchronous programming, FastAPI, and containerization via Docker.
• Hands-on experience with LLM orchestration frameworks like LangChain, LlamaIndex, or DSPy.
• Strong understanding of modern NLP techniques, embedding models, vector spaces, and semantic search.
• Experience deploying production applications on AWS, GCP, or Azure, utilizing managed Kubernetes or serverless containers.
• Bachelor's or Master's degree in Computer Science, Data Science, or a related quantitative technical field.
• Bonus: Experience with vLLM, TensorRT-LLM, custom model hosting, or contribution to open-source GenAI frameworks.