LLM Engineer

We are seeking a skilled and experienced LLM Engineer with 3-5 years of relevant experience in generative AI, large language models (LLMs), and AI application development. The ideal candidate will possess strong Python programming skills, a solid understanding of LLM architecture, and hands-on experience designing, developing, and deploying scalable AI-powered applications. We are looking for an engineer with strong technical fundamentals, practical problem-solving abilities, and the capability to translate complex business requirements into reliable, production-ready AI solutions.

Responsibilities:

• Design, develop, and deploy LLM-powered applications using commercial and open-source language models.
• Build and optimize end-to-end Retrieval-Augmented Generation (RAG) pipelines.
• Develop intelligent AI agents and multi-step workflows using modern AI frameworks.
• Implement prompt engineering, structured output generation, function calling, and tool integration.
• Design scalable backend services and APIs using Python and FastAPI.
• Optimize LLM applications for accuracy, latency, cost, and performance.
• Implement evaluation frameworks to assess response quality, retrieval performance, and hallucination rates.
• Integrate vector databases, semantic search, and knowledge retrieval systems.
• Implement appropriate guardrails, monitoring, logging, and error-handling mechanisms.
• Collaborate with cross-functional teams to deliver robust and scalable AI solutions.

Requirements:

• Strong analytical and problem-solving capabilities.
• Hands-on experience building and deploying production-grade LLM applications.
• The ability to explain technical architecture, implementation decisions, and engineering trade-offs.
• Strong coding skills and practical software engineering knowledge.
• The ability to independently troubleshoot complex technical challenges.
• Excellent technical communication and collaboration skills.

Programming and Backend Development:

• Strong proficiency in Python and software engineering fundamentals.
• Experience with FastAPI, REST APIs, asynchronous programming, and API integrations.
• Strong understanding of data structures, algorithms, object-oriented programming, and clean coding practices.

Large Language Models and Generative AI:

• Strong understanding of Transformer architecture, attention mechanisms, tokenization, and embeddings.
• Hands-on experience with LLMs such as GPT, Claude, Llama, or Mistral.
• Experience with prompt engineering, few-shot learning, structured outputs, and function calling.
• Understanding of context windows, inference parameters, and LLM limitations.

Retrieval-Augmented Generation (RAG):

• Hands-on experience developing end-to-end RAG applications.
• Experience with document ingestion, preprocessing, chunking, and embedding generation.
• Familiarity with vector databases such as FAISS, Pinecone, Qdrant, Chroma, or Weaviate.
• Understanding of semantic search, hybrid search, metadata filtering, and reranking.
• Ability to evaluate and improve retrieval quality and answer accuracy.

AI Frameworks and Agentic AI:

• Experience with LangChain, LangGraph, LlamaIndex, or equivalent frameworks.
• Understanding of AI agent architecture, tool calling, workflow orchestration, and state management.
• Experience designing reliable multi-step AI workflows with appropriate error handling and validation.

Evaluation and Optimization:

• Experience evaluating LLM outputs and improving application quality.
• Understanding of retrieval and response evaluation metrics.
• Familiarity with hallucination mitigation, guardrails, and output validation.
• Experience optimizing inference latency, token usage, and application cost.

Preferred Qualifications:

• Experience with fine-tuning techniques such as LoRA, QLoRA, SFT, or PEFT.
• Familiarity with Hugging Face Transformers and open-source model deployment.
• Knowledge of model quantization and inference optimization.
• Experience with Docker, Kubernetes, and cloud platforms such as AWS, Azure, or GCP.
• Familiarity with MCP (Model Context Protocol).
• Experience with LLM observability and evaluation tools.