LTM is hiring AI Software Engineers / Specialists โ Software Engineering to design, build, deploy, and operate production-grade Generative AI capabilities.
This opportunity is focused on engineers who can combine strong backend software engineering fundamentals with hands-on experience in Generative AI, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Agentic AI, and production delivery.
The primary technology stack includes Python, FastAPI, Flask, LLMs, and RAG, with a strong emphasis on taking AI solutions beyond prototypes and into reliable production environments.
The role is primarily targeted at candidates with around 6+ years of professional Python/backend/software engineering experience, with at least 1 year of hands-on production experience delivering LLM-enabled applications. The posting also mentions consideration for a P2-level profile with 4โ5 years of experience.
๐ Position Details
๐ข Company: LTM
๐ผ Position: Specialist โ Software Engineering / AI Engineer
๐ Job ID: 8908345
๐ Location: Bengaluru
๐จโ๐ป Experience Required:
โข Primary role โ 7 Years
โข Required qualification โ 6+ years of professional Python backend/software engineering experience
โข P2 consideration โ 4โ5 years of experience
๐ฏ Openings: 1
๐ Qualification: Not Mentioned
๐ข Employment Type: Not Mentioned
๐ Eligibility: Hands-on AI/software engineering experience with relevant backend, LLM, RAG, and production delivery skills
๐ง Apply Via: Not Mentioned
๐ ๏ธ Skills Required
โ
Python
โ
FastAPI
โ
Flask
โ
Generative AI
โ
Large Language Models (LLMs)
โ
RAG / Retrieval-Augmented Generation
โ
Agentic AI
โ
LLM APIs โ OpenAI / Anthropic / Amazon Bedrock
โ
LangChain / LangGraph / AutoGen / CrewAI / Microsoft Agent Framework
โ
Embeddings & Vector Databases
โ
Prompt Engineering & Prompt Debugging
โ
LLMOps / Observability / Telemetry
โ
REST APIs & Backend Services
โ
Cloud Deployment โ AWS / Azure / GCP
โ
CI/CD & Containerization
โ
Automated Testing
โ
Monitoring & Security Controls
โ
Java Microservices โ listed as a mandatory skill in the job posting
โ
Problem Solving & Debugging
โ
Communication & Cross-functional Collaboration
๐ Position Overview
The role focuses on building production-grade AI applications and services, with an emphasis on reliability, maintainability, performance, and measurable outcomes.
The selected engineer will work on solutions involving LLM integrations, RAG pipelines, agentic workflows, tool execution, workflow orchestration, memory, guardrails, and MCP-based integrations.
The position requires practical backend engineering capabilities along with the ability to diagnose and improve AI system behavior, including retrieval relevance, prompt behavior, hallucinations, context-window limitations, and token usage.
A key part of the role is production ownership. Engineers are expected to support AI-enabled services under real-world conditions such as traffic, rate limits, failures, changing model behavior, and operational requirements.
The role also includes using modern AI-assisted coding tools such as GitHub Copilot, Cursor AI, and Gemini Code Assist to accelerate development, code conversion, and version upgrades.
๐ฏ Key Responsibilities
๐น Design and develop Python services integrating LLM APIs such as OpenAI, Anthropic, and Amazon Bedrock.
๐น Build end-to-end RAG pipelines covering document ingestion, chunking, embeddings, vector search, retrieval, prompt construction, and response generation.
๐น Develop agentic AI capabilities using tool execution, workflow orchestration, memory, guardrails, and MCP-based integrations.
๐น Implement LLMOps practices including observability, telemetry, performance monitoring, and cost optimization.
๐น Develop robust REST APIs and backend services using FastAPI or Flask.
๐น Diagnose and improve response quality by analyzing prompts, retrieval relevance, hallucinations, context limitations, and token constraints.
๐น Build production resilience through retries, rate-limit handling, error management, observability, and operational support.
๐น Deploy AI-enabled features to cloud environments and take ownership of reliability, maintainability, and performance.
๐น Collaborate with product, architecture, engineering, and quality teams to translate use cases into secure, usable, and testable solutions.
๐น Participate in code reviews, engineering standards, technical documentation, and continuous improvement of the AI delivery platform.
๐น Use AI pair-programming tools such as GitHub Copilot, Cursor AI, and Gemini Code Assist for development and modernization activities.
๐ง Required Experience
Candidates should have practical experience in the following areas:
โ 6+ years of professional experience in Python backend or software engineering.
โ At least 1 year of hands-on production experience delivering LLM-enabled features or applications.
โ Experience with agent frameworks such as Microsoft Agent Framework (MAF), LangChain, LangGraph, AutoGen, or CrewAI.
โ Experience developing RAG pipelines using embeddings, vector databases, retrieval strategies, and prompt orchestration.
โ Strong Python development skills with practical FastAPI or Flask experience.
โ Production integration experience with OpenAI, Anthropic, or Amazon Bedrock.
โ Practical understanding of prompt debugging, context-window constraints, token management, hallucination mitigation, and model response evaluation.
โ Experience shipping user-facing features and supporting them in production.
โญ Preferred Qualifications
โ Experience with LangChain or LlamaIndex
โ Experience with vector databases such as Pinecone, Weaviate, or ChromaDB
โ Experience building rapid prototypes or demonstrations with Streamlit
โ Cloud deployment experience on AWS, Microsoft Azure, or Google Cloud Platform
โ Familiarity with CI/CD, containerization, monitoring, security controls, and automated testing for AI services
๐ What Success Looks Like
According to the role description, success in this position involves:
โ AI features being delivered as working and maintainable product capabilities rather than only prototypes.
โ Services remaining reliable under production traffic, rate limits, failures, and changing model behavior.
โ Continuous improvement of response quality through systematic evaluation, retrieval tuning, prompt refinement, and defect resolution.
โ Clear, testable, documented code aligned with engineering standards.
The ideal candidate is described as a hands-on engineer who enjoys building, debugging, and operating AI features, with a strong focus on working software and measurable outcomes.
๐ฑ Why This Role Can Be Valuable for AI Engineers
๐ Hands-on exposure to production Generative AI engineering
๐ Practical experience with LLM-powered applications
๐ Opportunity to work on RAG architectures and retrieval systems
๐ Exposure to Agentic AI and tool-based workflows
๐ Experience working with enterprise LLM APIs
๐ Opportunity to build scalable Python backend services
๐ Exposure to cloud deployment and LLMOps practices
๐ Experience with modern AI-assisted development tools
๐ Opportunity to work across product, architecture, engineering, and quality teams
๐ Practical exposure to production reliability and AI system optimization
๐ฐ Salary Range
๐ต Salary: Not Mentioned
No salary estimate has been added because compensation details were not included in the provided job information.
๐งช Expected Interview Rounds
The exact interview process has not been mentioned in the job posting. Candidates may generally expect some combination of:
1๏ธโฃ Resume Shortlisting
2๏ธโฃ HR Screening
3๏ธโฃ Technical Assessment
4๏ธโฃ Technical Interview
5๏ธโฃ Managerial / Final Discussion
6๏ธโฃ HR Discussion & Documentation
โ ๏ธ These are general/expected interview stages and are not confirmed LTM-specific rounds.
๐ Preparation Tips for AI Engineer Interviews
โ Revise advanced Python concepts, including OOP, exception handling, concurrency, APIs, and backend development.
โ Prepare FastAPI / Flask concepts and REST API design.
โ Understand the complete RAG lifecycle from document ingestion to final response generation.
โ Revise embeddings, vector search, chunking strategies, metadata filtering, and retrieval techniques.
โ Prepare practical concepts around LLMs, prompt engineering, context windows, tokens, hallucinations, and model evaluation.
โ Understand agentic AI concepts such as tools, memory, orchestration, workflows, and guardrails.
โ Review one or two practical projects where you integrated an LLM API into an application.
โ Prepare questions around rate limiting, retries, failures, monitoring, observability, and production resilience.
โ Understand vector databases such as Pinecone, Weaviate, or ChromaDB.
โ Be ready to discuss cloud deployment, CI/CD, containers, automated testing, and monitoring.
โ Review Java Microservices concepts because the posting explicitly lists Java Microservices under mandatory skills.
โ Prepare examples demonstrating debugging, problem solving, collaboration, and production ownership.
๐ Resume Tips for This Role
โ Highlight production-level Python backend experience.
โ Clearly mention hands-on LLM / Generative AI projects.
โ Add specific experience with RAG pipelines and vector databases.
โ Mention LLM APIs used, such as OpenAI, Anthropic, or Amazon Bedrock.
โ List agent frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or MAF where applicable.
โ Highlight FastAPI / Flask experience.
โ Mention cloud platforms and deployment experience.
โ Include LLMOps, monitoring, observability, CI/CD, and automated testing experience where applicable.
โ Add measurable technical achievements wherever possible.
โ Tailor the resume around AI engineering + backend engineering + production ownership.
โ Frequently Asked Questions (FAQs)
Q1. What is the job title?
The position is Specialist โ Software Engineering, focused on AI product engineering.
Q2. What is the Job ID?
The Job ID provided is 8908345.
Q3. Where is the job located?
The listed location is Bengaluru.
Q4. How many openings are available?
The posting mentions 1 opening.
Q5. What experience is required?
The primary requirement is around 6+ years of professional Python backend/software engineering experience, with the listing showing 7 years for the role. A P2 profile with 4โ5 years is also mentioned.
Q6. Is Generative AI experience required?
Yes. The role requires at least 1 year of hands-on experience delivering LLM-enabled features or applications to production.
Q7. Which AI technologies are relevant?
The role focuses on LLMs, RAG, Agentic AI, LLMOps, embeddings, vector search, prompt orchestration, and MCP-based integrations.
Q8. Which backend technologies are required?
The primary backend stack includes Python, FastAPI, and Flask.
Q9. What are the mandatory skills listed in the posting?
The job listing specifically shows Java Microservices under Mandatory Skills, while the role description emphasizes Python backend and Generative AI technologies.
Q10. Is the salary mentioned?
No. Salary information was not provided in the job details.
๐ Career Exposure in This Role
โจ Generative AI application engineering
โจ LLM integration and production deployment
โจ RAG pipeline development
โจ Agentic AI implementation
โจ Python backend engineering
โจ Cloud-based AI services
โจ LLMOps and observability
โจ AI reliability and performance optimization
โจ AI-assisted software development
โจ Enterprise production engineering
๐ฉ How to Apply
๐ Application Link: Click here
๐ Include in Your Email/Application:
โข Position Applying For
โข Total Experience
โข Current Location
โข Notice Period
โข Updated Resume
โข Contact Number
โข Relevant AI / LLM / RAG Experience
โ ๏ธ Please use the official LTM application channel or the original job-posting source because no email address or application link was included in the information provided here.
