Senior Specialist - AI Engineer

LTM; Maharashtra; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

LTM is seeking an experienced AI Engineer to build, integrate, and deploy enterprise AI applications that leverage multiple third-party AI models within client workflows. The role combines AI engineering with back-end development and forward deployment to ensure production-ready solutions deeply integrated with enterprise systems.

You will work with client engineering teams to deploy, configure, and optimize AI solutions, develop reusable SDKs and APIs, and ensure scalable, low-latency

Qualifications

• Experience building AI-powered enterprise applications for production use.
• Ability to integrate multiple AI services (LLMs, video AI, speech AI, vision AI) into client workflows.
• Strong backend engineering with API design, orchestration and deployment in cloud environments.

Responsibilities

• Build AI-enabled applications using enterprise-grade software practices.
• Integrate multiple third-party AI services including LLMs and other AI modalities.
• Develop orchestration logic across AI providers, APIs and enterprise apps.
• Implement AI workflows, prompt chains and business-rule execution.
• Collaborate with client engineers to deploy and optimize AI solutions.

Skills

Python programming

FastAPI

CI/CD practices

Client collaboration

Tools

OpenAI

Gemini

Claude

LangChain

LangGraph

Pinecone

Weaviate

Milvus

PostgreSQL

Redis

Docker

Kubernetes

AWS

Azure

GCP

Job description

Role Summary- Build, integrate and deploy enterprise AI applications that leverage multiple third-party AI models within client workflows. The role combines AI engineering, backend engineering and forward deployment responsibilities, ensuring AI solutions are production-ready, deeply integrated with enterprise systems and rapidly adaptable to customer environments.

Key Responsibilities

• Build AI-enabled applications using enterprise-grade software engineering practices.
• Integrate multiple third-party AI services including LLMs, video AI, speech AI and vision AI.
• Develop orchestration logic across AI providers, APIs and enterprise applications.
• Implement AI workflows, prompt chains, agentic workflows and business-rule execution.
• Work directly with client engineering teams to deploy, configure and optimize AI solutions.
• Develop reusable SDKs, APIs and integration accelerators.
• Troubleshoot customer deployments and production issues.
• Collaborate with Solution Architects, Backend Engineers, DevOps and Product teams.

AI Engineering Responsibilities

• Prompt engineering and prompt optimization.
• RAG implementation, embeddings and semantic retrieval.
• Model evaluation, response validation and confidence scoring.
• AI guardrails, safety checks and fallback mechanisms.
• Workflow orchestration using LangGraph, LangChain or equivalent frameworks.
• Deploy AI platforms into client cloud environments.
• Integrate with enterprise APIs, MAM, CMS, DAM, CRM and workflow systems.
• Customize AI workflows for client-specific business processes.
• Support production rollouts, customer pilots and enterprise onboarding.
• Partner with customer architects to resolve integration challenges.

Technical Skills

• Python (mandatory), FastAPI, REST APIs and microservices.
• Experience integrating OpenAI, Gemini, Claude, video AI or speech AI platforms.
• LangChain, LangGraph, CrewAI or similar orchestration frameworks.
• Vector databases (Pinecone, Weaviate, Milvus or equivalent).
• PostgreSQL, Redis and API integrations.
• Docker, Kubernetes and cloud platforms (AWS/Azure/GCP).
• Git, CI/CD and software engineering best practices.

Preferred Experience

• Enterprise SaaS, AI platforms, workflow automation, media technology, OTT or content operations.
• Experience working directly with enterprise customers and solution deployments.

Success Measures

• Rapid delivery of AI-powered business workflows.
• Successful customer deployments and production adoption.
• Reusable, scalable AI integrations across multiple enterprise clients.
• High reliability, low latency and maintainable production code.

AI-Driven Coding & Engineering Practices (Mandatory)

• Demonstrated experience using AI coding assistants such as GitHub Copilot, Cursor, Windsurf, Claude Code or equivalent.
• Leverage AI to accelerate software design, coding, API development, documentation, testing, debugging and refactoring while maintaining enterprise-grade quality.
• Review, validate and secure AI-generated code for correctness, performance, maintainability and security before production deployment.
• Use prompt engineering techniques to improve engineering productivity and software quality.
• Apply AI-assisted troubleshooting, root-cause analysis and performance optimization for production systems.
• Follow AI-assisted SDLC best practices while maintaining coding standards, version control and peer review discipline.