Artificial Intelligence Engineer

Coherent; Hyderabad; Hybrid; INR 2,500,000 - 4,000,000; Full time

Job summary

Coherent is seeking an experienced software engineer to build generative AI applications using LLM APIs, prompt workflows, and RAG pipelines. You will design and implement backend services in Python (FastAPI/Flask) and integrate with enterprise systems and tools.

The role emphasizes practical AI deployments, data preparation, and pipeline optimization, with focus on latency, robustness, and scalable architecture. Hyderabad-based on-site position with cloud and web tech exposure.

Qualifications

• 5 years of software engineering / applied AI experience.
• Hands-on cloud tech experience (Microsoft Azure / AWS / Google).
• Strong hands-on experience in Python and modern web stacks.

Responsibilities

• Build and maintain Generative AI applications using LLM APIs, prompt workflows, RAG pipelines, and agent-based orchestration.
• Develop backend services, APIs, and microservices in Python (FastAPI/Flask).
• Implement enterprise AI use cases: assistants, Q&A, copilots, workflow automation, tool-using agents.

Skills

Python

Pyspark

Node.js

React

Angular

Flask

LLM

Generative AI

FastAPI

Education

Bachelor's degree in Computer Science / AI / Data Science

Tools

LangChain

LangGraph

CrewAI

Phidata

LlamaIndex

Job description

Role & responsibilities

• Build and maintain Generative AI applications using LLM APIs, prompt workflows, RAG pipelines, and agent-based orchestration.
• Develop backend services, APIs, and microservices in Python using frameworks such as FastAPI or Flask.
• Implement use cases such as enterprise assistants, document Q&A systems, internal copilots, workflow automation tools, and tool-using AI agents.
• Integrate AI applications with enterprise systems, databases, APIs, and external tools.
• Collect, clean, preprocess, and structure datasets used for AI workflows, retrieval pipelines, evaluation, and application inputs.
• Develop and maintain data and feature pipelines that support retrieval quality, model inputs, inference workflows, and application consistency
• Support preparation of knowledge sources for RAG systems, including chunking, indexing, metadata design, and retrieval optimization.
• Implement MCP-style tool usage patterns, connectors, APIs, and tool-enabled workflows where applicable.
• Participate in testing, evaluation, logging, monitoring, debugging, and ongoing improvement of AI applications.
• Help optimize AI systems for latency, response quality, hallucination reduction, robustness, and token efficiency.

Preferred candidate profile

• Bachelors degree in computer science, Artificial Intelligence, Data Science, Engineering, or a related field.
• 5 years of experience in software engineering, applied AI, ML engineering, or related development roles.
• Hands-on experience with one more cloud technology - Microsoft, AWS, Google
• Strong hands-on experience in 2 more skills - Python, Pyspark, Node.js, React, Angular, Flask
• Good practical understanding of LLM-based applications and Generative AI implementation.
• Experience with some of the following: prompt engineering, RAG pipelines, vector databases, agent frameworks, API integration, Python backend development, and data preparation or workflow pipelines.
• Familiarity with frameworks and tools such as LangChain, LangGraph, CrewAI, Phidata, LlamaIndex, or similar.
• Experience building REST APIs or backend services using FastAPI, Flask, or similar frameworks.
• Good understanding of JSON, structured data flows, APIs, and service-oriented design.
• Proficiency in SQL and relational databases, along with experience in managing unstructured data using NoSQL or vector databases for AI model training and retrieval.
• Strong problem-solving skills and willingness to learn quickly