Genai Engineer

Augury Augury · Vertical AI · Augury India · R&D

The GenAI Engineer for AgenticAI will work on combining AgenticAI with Industrial AI to solve manufacturing challenges. Responsibilities include owning the end-to-end lifecycle of GenAI and AgenticAI solutions, building intelligent systems with LLMs, embeddings, agents, and RAG pipelines, and deploying these solutions in production. The role requires strong Python skills, experience with GenAI frameworks, and familiarity with MLOps/LLMOps.

What you'd actually do

  1. Own the end-to-end development lifecycle of GenAI and AgenticAI solutions, from experimentation and prototyping through deployment and monitoring.
  2. Build intelligent systems that combine time-series modeling, signal processing, and GenAI technologies including LLMs, embeddings, agents, orchestration frameworks, and retrieval pipelines.
  3. Design and implement LLM-powered workflows such as RAG pipelines, tool usage, multi-agent orchestration, and evaluation frameworks at scale.
  4. Develop AgenticAI applications that integrate diverse data sources, including sensor-based time-series data, unstructured text, and machine learning outputs.
  5. Drive technical decision-making across architecture, tooling, experimentation strategy, and deployment patterns for AgenticAI systems.

Skills

Required

  • Python
  • GenAI frameworks (LangChain, CrewAI, AutoGen, LangGraph)
  • LLM-based workflows (prompting, embeddings, RAG, tool calling, orchestration, evaluation)
  • Observability and experimentation tooling (LangSmith)
  • Building and deploying GenAI/AgenticAI applications in production
  • Backend services (REST, gRPC)
  • Software engineering principles (CI/CD, distributed systems)

Nice to have

  • Master’s degree
  • Industrial systems, IoT platforms, digital twins, or manufacturing technologies
  • Time-series modeling, anomaly detection, predictive maintenance, or sensor analytics
  • Streaming infrastructure (Kafka, NSQ)
  • Data platforms (Databricks, BigQuery, Snowflake)
  • Knowledge graphs
  • Multimodal AI systems
  • Cloud-native development patterns
  • Scalable AI infrastructure

What the JD emphasized

  • Hands-on experience building and deploying GenAI or AgenticAI applications in production environments.
  • Strong experience with GenAI frameworks such as LangChain, CrewAI, AutoGen, LangGraph, or similar ecosystems.
  • Experience implementing LLM-based workflows including prompting, embeddings, RAG, tool calling, orchestration, and evaluation systems.
  • Experience with observability and experimentation tooling such as LangSmith or equivalent platforms.

Other signals

  • GenAI Engineer
  • AgenticAI
  • end-to-end lifecycle
  • production deployment
  • LLM-powered workflows
  • RAG pipelines
  • tool usage
  • multi-agent orchestration
  • evaluation frameworks
  • MLOps and LLMOps