LLM Engineer – LLM & Generative AI

About the job

About Our Company:

Aerocraft Engineering India Pvt Ltd based in Ahmedabad, provides services to US-based Architecture, Engineering, and Construction groups of companies:

• Russell and Dawson An Architecture/Engineering/Construction firm (www.rdaep.com)
• United-BIM BIM Modeling Services Firm (www.united-bim.com)
• AORBIS Procurement as a Service Provider (www.aorbis.com)

We are a nimble and growing organization where everyones role is very important for the companys business success. All team members contributions have a direct correlation with the companys performance in meeting its business and financial objectives.

We are looking for an Experienced AI Engineer with hands-on experience building production-grade applications powered by Large Language Models. You will design, develop, and optimize LLM-based systems with a strong focus on scalable Retrieval-Augmented Generation (RAG) pipelines and model fine-tuning to

deliver intelligent solutions that drive real business impact.

Experience Required - Minimum 3+ Years

Job Location:

• Ahmedabad (Siddhivinayak Towers, Makarba)

Shift Timings:

• 11am to 8pm/ 9am to 6pm (Shift may change as per business requirement)
• Monday to Friday
• Work from office

Immediate Joiner is Preferred.

Key Responsibilities

• Design, build, and maintain scalable RAG systems for knowledge-intensive applications, including document ingestion, chunking strategies, vector store management, and retrieval optimization.
• Fine-tune open-source and proprietary LLMs using parameter-efficient techniques such as LoRA and QLoRA to adapt models for domain-specific use cases.
• Develop and deploy end-to-end LLM-powered applications including chatbots, agents, summarization tools, and search systems.
• Evaluate model performance using quantitative metrics (BLEU, ROUGE, perplexity) and qualitative benchmarks; iterate on prompt engineering and fine-tuning strategies accordingly.
• Optimize inference pipelines for latency, cost, and throughput across cloud and on-premise environments.
• Collaborate with data engineers, product managers, and stakeholders to translate business requirements into AI-driven solutions.
• Stay current with rapidly evolving LLM research, tools, and frameworks, and advocate for best practices across the team.

Must-Have Requirements

• 3+ years of experience in AI/ML engineering, with at least 3+ year focused on LLMs and generative AI.
• Proven experience developing scalable RAG systems (vector databases such as Pinecone, Weaviate, Qdrant, Chroma DB, or FAISS; embedding models; retrieval and re-ranking strategies).
• Hands-on experience with model fine-tuning using LoRA, QLoRA, or similar PEFT techniques on frameworks like Hugging Face Transformers, PEFT, or Axolotl.
• Strong proficiency in Python and ML frameworks (PyTorch, Transformers, LangChain, LlamaIndex).
• Solid understanding of transformer architectures, attention mechanisms, and tokenization.
• Experience with cloud platforms (AWS, GCP, or Azure) for model training and deployment.

Nice-to-Have

• Experience with multi-agent frameworks (AutoGen, CrewAI, LangGraph).
• Familiarity with model serving tools such as vLLM, TGI, or Triton Inference Server.
• Knowledge of MLOps practices experiment tracking (W&B, MLflow), CI/CD for ML, and model monitoring.
• Experience with quantization techniques (GPTQ, AWQ, GGUF) for efficient deployment.
• Contributions to open-source AI/ML projects.

Benefits:

Exposure to US Projects/Design/Standards

Company provides Dinner/Snacks/Tea/Coffee

5 Days Working Week

15 paid leave annually & 8-10 Public Holidays