NLP Engineer

LLM Engineer : (1-3 years)

About the Role

We are looking for an LLM Engineer to design and deploy large language model solutions that power resume parsing, job description understanding, semantic search, and candidate-job matching. Youwill be responsible for developing scalable NLP / LLM workflows, optimizing models for production, and integrating cutting-edge GenAI advancements into TurboHire’s recruitment intelligence platform.

Responsibilities

Design and implement LLM-powered NLP pipelines for parsing resumes, job descriptions, and other unstructured recruitment text.

Build scalable systems for information extraction, entity recognition, text classification, and semantic similarity.

Fine-tune and optimize large language models (e.g., GPT, LLaMA, Falcon, Mistral) for domain-specific applications.

Develop retrieval-augmented generation (RAG) pipelines with vector databases to enhance semantic search and candidate-job matching.

Collaborate with software and ML engineers to productionize LLM applications, ensuring high reliability, low latency, and cost efficiency.

Conduct in-depth text data analysis to uncover insights and improve model performance.

Continuously evaluate and integrate advances in transformer architectures, embeddings, and LLM toolchains.

Establish monitoring, evaluation, and safety frameworks to address drift, hallucination, and bias in LLM outputs

Requirements

Bachelor’s or Master’s degree in Computer Science, Data Science, AI / ML, or related field.

3–5 years of experience in NLP, GenAI, or LLM engineering, with proven exposure to real-world parsing or information extraction.

Strong programming skills in Python and familiarity with NLP / LLM frameworks (HuggingFace Transformers, LangChain, LlamaIndex, spaCy).

Hands-on experience with deep learning frameworks (PyTorch, TensorFlow).

Experience with vector databases (FAISS, Pinecone, Weaviate, Milvus) and embedding-based retrieval.

Prior experience deploying LLM-powered applications (chatbots, semantic search,resume / job parsing, or similar).

Understanding of GPU acceleration, distributed inference, and model optimization.

Familiarity with ranking and retrieval metrics (e.g., precision@k, NDCG) and evaluation ofLLM outputs

Knowledge of data privacy, fairness, and bias mitigation in AI systems.

Strong collaboration and communication skills to work with product and engineering teams.