DT - AI​/LLM Engineer

We are seeking an experienced AI/LLM Engineer with expertise in building, fine-tuning, and deploying state-of-the-art Large Language Model (LLM) solutions. The ideal candidate will have hands-on experience in prompt engineering, RAG pipelines, multi-agent orchestration frameworks, knowledge graph reasoning, and model evaluation methodologies. You will play a critical role in designing intelligent, scalable, and safe AI-driven systems for real-world applications.

LLM Development & Fine-Tuning

Fine-tune large language models on domain-specific datasets.

Optimize prompts and context strategies to maximize performance across diverse use cases.

Implement and evaluate RAG (Retrieval-Augmented Generation) pipelines for knowledge-grounded AI responses.

Multi-Agent Orchestration

Build and manage multi-agent AI systems using frameworks such as Lang Chain, Auto Gen, CrewAI, and Haystack.

Design intelligent workflows where multiple AI agents collaborate, coordinate, and reason effectively.

Knowledge Graphs & Reasoning

Construct and maintain knowledge graphs to enhance contextual reasoning and factual grounding of LLMs.

Integrate graph-based reasoning with LLM pipelines for improved interpretability and accuracy.

Evaluation & Safety

Develop robust evaluation pipelines for hallucination detection, factual alignment, safety, and ethical compliance.

Define metrics and benchmarks for continuous monitoring and quality assurance of deployed models.

• Strong expertise in LLM fine-tuning, prompt engineering, and RAG pipelines.
• Proficiency with multi-agent orchestration frameworks (Lang Chain, Auto Gen, CrewAI, Haystack).
• Hands-on experience with knowledge graph construction, reasoning, and integration into AI pipelines.
• Familiarity with model evaluation techniques related to hallucination, factual alignment, and AI safety.
• Proficiency in Python and modern ML/NLP libraries (PyTorch, Tensor Flow, Hugging Face Transformers, etc.).
• Solid understanding of vector databases (FAISS, Pinecone, Weaviate, Milvus).
• Strong problem-solving, analytical, and system design skills.

• Advanced degree (MS/PhD) in Computer Science, AI/ML, Data Science, or related field.
• Experience with cloud platforms (AWS, GCP, Azure) and scalable ML deployment.
• Contributions to open-source AI/NLP projects.
• Research experience in trustworthy AI, safety alignment, or autonomous agent design.