Job Summary
We are seeking a Assistant manager - AI Engineer with strong hands-on experience in designing, building, and deploying production-grade LLM and multi-agent systems. The ideal candidate will have expertise in architecting autonomous agents for generation, evaluation, orchestration, and workflow automation, with a strong focus on reliability, scalability, governance, and human-in-the-loop controls.
The role requires deep technical expertise in Python, Large Language Models (LLMs), Agentic AI frameworks, RAG, vector search, prompt engineering, LLM evaluation, and guardrails.
Key Responsibilities
- Design and implement scalable multi-agent architectures involving generation agents, evaluation/critic agents, orchestration agents, and autonomous workflow systems.
- Build and deploy LLM-powered applications and generation pipelines that deliver reliable, high-quality outputs at scale.
- Develop LLM-as-a-Judge, critic-agent, and automated evaluation frameworks to assess output quality, accuracy, compliance, and reliability.
- Design and implement effective prompt engineering, grounding, Retrieval-Augmented Generation (RAG), and vector search strategies using trusted enterprise data.
- Build robust agent orchestration workflows using frameworks such as LangGraph, LangChain, CrewAI, AutoGen, or similar technologies.
- Implement human-in-the-loop approval gates, feedback mechanisms, and continuous improvement loops to enhance agent performance and reliability.
- Design and implement AI guardrails, validation layers, content governance, and Responsible AI controls for production-grade systems.
- Integrate and optimize solutions using major LLM providers and APIs, selecting appropriate models based on quality, latency, scalability, and cost requirements.
- Deploy and manage LLM and agent-based applications on cloud AI/ML platforms such as Databricks Mosaic AI, Model Serving, or similar platforms.
- Establish LLMOps and MLOps practices, including experiment tracking, prompt/version management, model monitoring, tracing, evaluation, and observability.
- Optimize AI systems for performance, latency, token usage, infrastructure cost, and output quality.
- Collaborate with data engineering, ML engineering, platform, product, and business teams to translate business requirements into scalable Agentic AI solutions.
Required Skills
- Strong hands-on experience with Python and building LLM-powered applications in production environments.
- 6 to 10 Years of Experience in Ai Engineering & Data Science Analytics.
- Strong experience designing and implementing Agentic AI and multi-agent systems.
- Hands-on expertise with multi-agent and orchestration frameworks such as LangGraph, LangChain, CrewAI, AutoGen, or similar frameworks.
- Strong knowledge of Prompt Engineering, Retrieval-Augmented Generation (RAG), grounding techniques, vector databases, and semantic search.
- Experience working with major LLM providers and APIs, with a strong understanding of model selection and trade-offs related to cost, latency, performance, and quality.
- Hands-on experience with LLM evaluation frameworks, including LLM-as-a-Judge, critic agents, automated evaluation, and quality assessment techniques.
- Strong understanding of AI guardrails, validation frameworks, Responsible AI, content governance, and safety controls.
- Experience implementing human-in-the-loop workflows and feedback mechanisms for AI systems.
- Experience deploying LLMs and Agentic AI applications on cloud ML/AI platforms such as Databricks Mosaic AI, Model Serving, or equivalent platforms.
- Knowledge of MLOps / LLMOps practices, including experiment tracking, prompt management, version control, monitoring, tracing, and observability.
- Strong understanding of AI application performance optimization, including latency, scalability, token consumption, and cost optimization.
- Experience taking AI/LLM applications from prototype or proof-of-concept stages to production deployment.
- Strong problem-solving skills and the ability to work collaboratively with cross-functional engineering and business teams.
Why Join Us?
- Opportunity to design and build next-generation Agentic AI and multi-agent systems for enterprise-scale use cases.
- Work on cutting-edge technologies involving LLMs, autonomous agents, RAG, AI orchestration, and intelligent workflow automation.
- Exposure to modern LLMOps, MLOps, AI evaluation, observability, and Responsible AI practices.
- Opportunity to take innovative AI solutions from prototype to production and solve complex real-world business problems.
- Collaborative environment with opportunities to work closely with AI, data engineering, machine learning, platform, and business teams.
- Culture that encourages innovation, experimentation, continuous learning, technical excellence, and ownership.
We are an equal opportunity employer and value diversity at our company. We do not discriminate on the basis of race, religion, color, national origin, sex, gender, gender expression, sexual orientation, age, marital status, veteran status, or disability status.
