LLM Engineer

LLM Engineer

Location: Bangalore

Employment Type: Full-Time

Experience: 25 Years

Department: Engineering

Role Overview

We are looking for an experienced LLM Engineer to design and build scalable, production-grade systems powered by large language models. This role involves developing robust generative AI solutions, building internal tools and APIs, and ensuring reliable deployment of LLM-driven applications across real-world workflows.

Key Responsibilities

LLM Application Development

• Design and implement LLM-powered features including assistants, automated workflows, and intelligent tools
• Build internal platforms and APIs to support scalable LLM integrations
• Develop modular workflows using techniques such as RAG, prompt chaining, and structured prompting

Model Optimization & Performance

• Evaluate model performance using automated metrics and human feedback
• Optimize latency, cost, and reliability using batching, caching, and fallback strategies
• Improve context management and prompt performance across use cases

Production Deployment & Observability

• Deploy and manage LLM-powered services in production environments
• Integrate observability, monitoring, and usage analytics frameworks
• Manage prompt versioning, configuration tracking, and multi-model experimentation

Architecture & Engineering Collaboration

• Work closely with engineering, product, and research teams to deliver end-to-end AI solutions
• Build scalable architecture for reliable and secure AI deployments
• Contribute to internal frameworks, guidelines, and best practices for LLM usage

Governance & Responsible AI

• Implement guardrails and safety frameworks for responsible AI usage
• Ensure reliability, compliance, and robustness of LLM systems in production environments
• Support development of standards for secure and ethical AI implementation

Required Skills & Qualifications

• Bachelors degree in Computer Science, Information Technology, or related field
• Strong understanding of LLM architectures, inference workflows, and prompt engineering techniques
• Strong programming skills in Python
• Experience working with frameworks such as LangChain, Haystack, or similar
• Experience integrating OpenAI, Anthropic, or open-source LLM models into production environments
• Understanding of agentic workflows, context handling, and prompt orchestration
• Familiarity with cloud platforms such as AWS or GCP
• Experience with containerization technologies such as Docker or Kubernetes
• Strong problem-solving and cross-functional collaboration skills

Preferred Skills

• Experience building AI-powered assistants or user-facing LLM applications
• Familiarity with emerging LLM protocols and agent-based architectures
• Experience working in regulated environments such as healthcare
• Understanding of observability, monitoring, and experimentation frameworks
• Experience working in Agile development environments