Staff Engineer

Saur Energy International; Bengaluru; Hybrid; INR 2,500,000 - 4,000,000; Full time

Job summary

Saur Energy International in Bengaluru seeks a skilled AI/GenAI Engineer to design, implement, and optimize AI agents using LLMs, RL, and planning frameworks. You will build scalable multi-agent architectures, integrate with APIs and databases, and deploy reliable AI-driven systems in production.

Ideal candidates hold a Masters/PhD in CS/AI and 5+ years in AI/genAI, with hands-on experience in LangChain, OpenAI APIs, PyTorch, TensorFlow, and cloud deployment using Docker/Kubernetes.

Qualifications

• Masters/ PhD in Computer Science, AI/ML, Engineering, Mathematics, or related field.
• 5+ years of relevant experience in AI/GenAI development.
• 3+ years in AI GenAI development & deployment with autonomous agent systems.
• Experience designing GenAI apps with agent orchestration, multi-step reasoning, prompt engineering, RAG integration, and model selection.
• Strong fundamentals in ML engineering and system architecture.

Responsibilities

• Design, implement, and optimize AI agents using LLMs, RL, planning, and decision frameworks.
• Develop scalable multi-agent architectures supporting long horizon reasoning, autonomy, planning, interaction, and complex tasks.
• Integrate AI Agents with APIs, backend services, databases, and enterprise applications.
• Prototype, deploy, and maintain AI-driven systems ensuring reliability and performance in production environments.
• Optimize agent behavior through continuous feedback, reinforcement learning, and user interaction.
• Collaborate with research, engineering, product, and deployment teams to iterate on agent capabilities and innovate continuously.
• Monitor AI Agent performance, evaluations, implement safety guardrails, and ensure ethical AI practices.
• Document AI Agent architectures, design decisions, workflows, and maintain technical documentation.
• Stay current with emerging AI technologies, contribute to platform and tooling improvements, and share knowledge.
• Push the boundaries of planning, reasoning, and agentic intelligence by designing large-scale AI/ML solutions integrating state-of-the-art research.

Skills

Python

JavaScript/TypeScript

Node.js

Java

Go

LangChain

OpenAI APIs

PyTorch

TensorFlow

LLMs

Prompt engineering

NLP

Agent orchestration

Multi-agent systems

AutogenAI

LangGraph

MCP protocol

Vector databases

Semantic retrieval

Real-time data pipelines

Docker

Kubernetes

AWS

Google Cloud

Model training

Fine-tuning

Evaluation techniques

AI ethics

Data privacy

Secure data handling

Education

Masters/ PhD in Computer Science, AI/ML, Engineering, Mathematics, or related field

Tools

LangChain

OpenAI APIs

PyTorch

TensorFlow

Job description

Key Responsibilities:

• Design, implement, and optimize AI Agents using LLMs, reinforcement learning, planning algorithms, and decision-making frameworks.

• Develop scalable multi AI Agent architectures supporting long horizon reasoning, autonomy, planning, interaction, and complex task completion.

• Integrate AI Agents with APIs, backend services, databases, and enterprise applications.

• Prototype, deploy, and maintain AI-driven systems ensuring reliability and performance in production environments.

• Optimize agent behavior through continuous feedback, reinforcement learning, and user interaction.

• Collaborate closely with research, engineering, product, and deployment teams to iterate on agent capabilities and innovate continuously.

• Monitor AI Agent performance, conduct rigorous evaluations, implement safety guardrails, and ensure ethical AI practices.

• Document AI Agent architectures, design decisions, workflows, and maintain comprehensive technical documentation.

• Stay current with emerging AI technologies, contribute to platform and tooling improvements, and share knowledge within the team.

• Your mission is to push the boundaries of planning, reasoning, and agentic intelligence. You will design and implement large-scale AI/ML solutions integrating the latest state of the art research in our global products

Core Technical Skills:

• Proficiency in Python and/or languages like JavaScript, TypeScript, Node.js, or Java, Go, with strong coding and software engineering practices.

• Expertise with AI/ML libraries and frameworks such as LangChain, OpenAI APIs, PyTorch, TensorFlow, commercial or open source LLMs.

• Hands-on experience with LLMs, prompt engineering, and natural language processing (NLP).

• Knowledge of agent orchestration platforms and multi-agent systems (e.g., AutogenAI, LangGraph, MCP protocol).

• Familiarity with data management, vector databases, semantic retrieval, and real-time data pipelines.

• Experience deploying AI systems on cloud platforms (AWS, Google Cloud) with container orchestration (Docker, Kubernetes).

• Strong understanding of machine learning model training, fine-tuning, and evaluation techniques.

• Awareness of AI ethics, data privacy, and secure handling of sensitive information.
  

Qualifications:

• Masters/ PhD degreein Computer Science, AI/ML,Engineering, Mathematics, or related field with5+ years of relevant experience.

• Minimum 3 years of experience in AI, GenAI application development & deployment particularly with autonomous agent systems or related AI software engineering roles.

• Demonstrated ability to work independently in fast-paced, experimental environments.

• Hands-on experience designing and building GenAI apps that allow users to experience AI use cases supporting features like agent orchestration, multi-step reasoning, prompt engineering, RAG integration, and model selection

• Expertise with LLMs and deep learning models, machine learning lifecycle management, data generation methods, model training & validation coupled with strong fundamentals and passion in software engineering and system architecture