Experience
5 - 7 yrs
Job Location
Bengaluru, India
Vacancy
1
Designation
Senior Artificial Intelligence Engineer
Job Type
ONSITE
Job Description
Job Summary
We are looking for an experienced Agentic AI Engineer to design, develop, and deploy production-grade AI agent systems powered by Large Language Models (LLMs). The role involves building autonomous multi-agent architectures that can generate, evaluate, and orchestrate content and workflows with strong validation mechanisms and human-in-the-loop controls.
The ideal candidate should have hands-on experience taking LLM-powered AI solutions from prototype to production, with expertise in agent frameworks, RAG pipelines, AI evaluation, and scalable AI engineering practices.
Roles Responsibilities
- Design and implement scalable multi-agent AI architectures, including generation, evaluation, and orchestration agents.
- Build and deploy LLM-powered generation pipelines that deliver reliable and high-quality outputs at scale.
- Develop LLM-as-a-Judge and critic-agent frameworks to evaluate AI outputs for quality, accuracy, and compliance.
- Engineer effective prompting, grounding, and Retrieval-Augmented Generation (RAG) strategies using trusted data sources.
- Implement human-in-the-loop workflows, approval mechanisms, and feedback loops to continuously improve agent performance.
- Optimize AI systems for cost, latency, scalability, and quality.
- Build observability frameworks with tracing, monitoring, and evaluation metrics for AI applications.
- Collaborate with data scientists, engineers, and business teams to deliver enterprise-grade AI solutions.
- Ensure responsible AI practices through guardrails, safety controls, and content governance mechanisms.
Primary Skills
Must-Have Skills:
- Strong proficiency in Python with hands-on experience developing production-grade AI applications.
- Experience building LLM-powered applications and generative AI solutions in production environments.
- Hands-on experience with multi-agent frameworks such as:
- LangGraph
- LangChain
- CrewAI
- AutoGen
- Strong understanding of Prompt Engineering
- Retrieval-Augmented Generation (RAG)
- Vector Databases / Vector Search
- AI grounding techniques
- LLM evaluation methodologies
- Experience with LLM-as-a-Judge patterns, critic agents, and AI quality evaluation frameworks.
- Knowledge of major LLM providers/APIs and understanding of model selection trade-offs.
Good-to-Have Skills:
- Experience deploying LLM applications on cloud ML platforms such as Databricks Mosaic AI, Model Serving platforms
- Exposure to MLOps / LLMOps practices, including: Experiment tracking, Prompt/version management, AI application observability
- Understanding of responsible AI principles, guardrails, and content governance.