LLM / GenAI Engineer

About The Role

The role focuses on building, optimizing, and scaling production-ready Generative AI systems. This includes moving beyond basic prompting to architect robust Retrieval-Augmented Generation (RAG) pipelines, multi-agent orchestrations, and systematic evaluation suites that ensure deterministic outputs from stochastic models. Working alongside infrastructure and backend teams, this position bridges the gap between state-of-the-art foundation models and scalable software engineering.

Key Responsibilities

• Arcitect and scale RAG pipelines using advanced retrieval strategies, document chunking, and semantic search integration with vector databases like Pinecone, Milvus, or pgvector.
• Implement and deploy multi-agent workflows and LLM orchestration utilizing frameworks such as LangChain, LlamaIndex, or Autogen.
• Design and execute systematic LLM evaluation and observability frameworks to monitor model drift, hallucination rates, and latency using tools like LangSmith or Phoenix.
• Fine-tune open-source models (such as Llama 3 or Mistral) using PEFT techniques like LoRA and QLoRA on domain-specific datasets.
• Optimize inference latency and throughput for model serving using specialized serving frameworks such as vLLM, TGI, or TensorRT-LLM.
• Collaborate with backend engineers to integrate AI services into existing microservice architectures via robust, asynchronous API layers using FastAPI or gRPC.

What We Are Looking For

• 3-6 years of software engineering experience, with at least 1.5 years dedicated to building and deploying LLM applications in a production environment.
• Strong software development fundamentals in Python, including experience with asynchronous programming, concurrent patterns, and automated testing frameworks.
• Hands-on experience with vector databases (Pinecone, Qdrant, Weaviate) and optimizing embeddings for semantic search and retrieval.
• Familiarity with fine-tuning techniques, hyperparameter optimization, and parameter-efficient transfer learning on open-weight models.
• Solid understanding of cloud infrastructure (AWS or GCP) and containerization technologies like Docker and Kubernetes.
• Bonus: Academic background in Computer Science or a related quantitative field; contributions to open-source GenAI frameworks or experience deploying models locally on edge devices.