Senior AI Engineer

Reltio

AI Infrastructure

Agentic Frameworks

Tech Stack

About the Role

About the Role

We are seeking a Senior Backend Engineer with a strong foundation in Java, solid Python capabilities, and hands-on experience building Agentic AI applications that integrate with Large Language Models (LLMs). This role blends traditional backend engineering expertise with next-generation AI agentic systems development, requiring not just system design skills, but also creativity in prompt engineering, AI product development and working with data-rich environments. You will contribute to the design and implementation of intelligent backend services that coordinate LLMs, agents, and data workflows to support enterprise-grade agentic systems.

Key Responsibilities

  • Develop robust, scalable Java/Python based backend systems that enable the orchestration of Agentic AI workflows.
  • Develop state-of-the-art AI/ML models for solving real-world data management challenges such as entity resolution, classification, similarity matching, and anomaly detection.
  • Integrate LLMs (e.g., OpenAI, Mistral, Claude, LLaMA) into backend pipelines to power autonomous or semi-autonomous decision-making.
  • Develop scalable ML workflows using Spark, MLlib, PyTorch, TensorFlow, or MLFlow, with seamless integration into production systems.
  • Work closely with various stakeholders to design agent architectures and LLM toolchains (using frameworks like LangGraph, Crew AI, AutoGen, etc.).
  • Implement services and APIs that manage prompt chaining, tool invocation, and contextual memory for agents.
  • Collaborate with data engineers to ensure clean, efficient, and real-time access to structured and semi-structured data.
  • Apply prompt engineering best practices to improve agent behavior, task accuracy, and adaptability.
  • Monitor and optimize service performance, reliability, and scalability in production environments.

Required Qualifications

  • 5+ years of overall experience in backend engineering, with strong proficiency in Java for scalable, distributed systems.
  • 2+ years of experience in developing and deploying machine learning models and AI products in production environments.
  • Experience in Agentic AI systems development using tools such as LangGraph, Crew AI, AutoGen, or similar.
  • Proficiency in Python (NumPy, scikit-learn, pandas, PyTorch/TensorFlow) and experience with large-scale data processing tools (Spark, Kafka, Airflow).

Preferred Qualifications

  • LLM orchestration framework experience (LangChain, LlamaIndex, RAG)
  • Microservices or data-rich platform development background
  • Vector database and embedding service familiarity
  • Cloud platform and DevOps proficiency
  • Experience building LLM-powered agents or copilots

Benefits

  • Comprehensive medical insurance (includes parents), accident and life coverage
  • Free telemedicine consultations and Employee Assistance Program
  • 36 annual leaves (18 sick, 18 earned)
  • 26 weeks maternity leave, 15 days paternity leave
  • One week annual recharge week globally
  • Home office setup allowance
  • Mobile and internet reimbursement
  • Free meals
  • Flexible hybrid work arrangement

Location: Bangalore, India

Apply Now
Apply Now

More jobs like this

Explore related roles

Get jobs like this weekly