Job Title : LLM Engineer

Experience : 4+ Years

Client : Pranatree

Location : Bangalore; Pune; Delhi (Hybrid - 3 days Office)

Employment Type : Contract

About the Role :

We are looking for a highly skilled LLM Engineer to design, develop, and optimize Large Language Model (LLM)-powered applications. This role requires deep expertise in LLM APIs, AI tool integrations, and vector database technologies. You will work with cutting-edge frameworks such as Lang Graph and DSPy, build tool-using AI systems, and leverage modern orchestration techniques to deliver intelligent, scalable, and high performance solutions.

Key Responsibilities :

- Design and develop LLM-powered applications integrating APIs such as Open AI, Claude, Gemini, etc.

- Build AI workflows using Lang Graph, DSPy, and tool-use frameworks.

- Implement MCP server integrations to extend LLM capabilities.

- Work with vector databases such as Qdrant, Milvus, or Pgvector for semantic search and retrieval.

- Optimize prompt engineering, model orchestration, and tool chaining for performance and accuracy.

- Collaborate with cross-functional teams to translate requirements into AI-enabled solutions.

- Ensure solutions adhere to best practices in security, scalability, and maintainability. - Use Azure DevOps for code management, CI/CD pipelines, and deployment.

- Participate in Agile ceremonies, sprint planning, and delivery reviews.

Required Skills & Qualifications :

- Bachelors or Masters degree in Computer Science, AI/ML, Engineering, or related field.

- 4+ years of experience in software development, with 2+ years in LLM/AI application development.

- Strong hands-on experience with LLM APIs (Open AI, Claude, Gemini, etc.).

- Experience with Lang Graph, DSPy, and tool-use patterns in AI systems.

- Knowledge of MCP server integration and usage.

- Expertise in vector databases (Qdrant, Milvus, Pgvector).

- Familiarity with Azure DevOps and Agile delivery methodologies.

Good to Have :

- Experience with RAG (Retrieval-Augmented Generation) pipelines.

- Knowledge of MLOps practices and AI model deployment.

- Familiarity with multi-cloud environments (Azure, AWS, GCP).

- Exposure to containerization (Docker, Kubernetes).

Why Join Us ?

- Work on cutting-edge AI and LLM engineering projects.

- Collaborate with top-tier AI engineers in a hybrid, innovation-driven environment.

- Build solutions that leverage the latest in tool-use AI, vector search, and orchestration frameworks.