Job Title: LLM Engineer
Job Type: Contract
Location: Hybrid Bangalore, Pune or Delhi
Job Summary
Join our customer's dynamic team as an LLM Engineer, where you'll leverage advanced language models and cutting-edge frameworks to build high-impact AI solutions. As a core contributor, you will help architect, deploy, and optimize LLM-powered applications using modern tools and methodologies in a collaborative, agile environment.
Key Responsibilities
- Design, develop, and deploy applications powered by large language models (LLMs) to solve real-world problems.
- Integrate and optimize LLM APIs with frameworks such as LangGraph and DSPy for enhanced tool orchestration.
- Implement and maintain vector databases (such as Qdrant, Milvus, or Pgvector) to support scalable data retrieval and storage operations.
- Collaborate effectively with team members using Azure DevOps, ensuring streamlined CI/CD pipelines and agile best practices.
- Work closely with cross-functional teams to understand requirements, deliver solutions, and contribute to architectural decisions.
- Troubleshoot, monitor, and enhance MCP server environments to ensure robust and reliable application performance.
- Continuously document solutions and communicate technical concepts clearly in both written and verbal formats.
Required Skills and Qualifications
- Proven experience developing with large language models (LLMs) in production environments.
- Hands-on proficiency with LangGraph and DSPy for advanced language model application workflows.
- Strong knowledge of LLM API integration and practical tool use in AI/ML pipelines.
- Expertise in deploying and managing vector databases such as Qdrant, Milvus, or Pgvector.
- Familiarity with Azure DevOps and agile development processes for efficient project execution.
- Demonstrated skill in maintaining and optimizing MCP server environments.
- Exceptional written and verbal communication skills, with a passion for clear, effective information exchange.
Preferred Qualifications
- Prior experience working in remote, distributed teams on AI-driven or SaaS products.
- Background in developing and deploying AI tools within enterprise-grade cloud ecosystems.
- Contributions to open-source LLM or AI infrastructure projects.
