Embedded AI platform engineer

Cyient; Maharashtra; On-site; INR 1,000,000 - 1,500,000; Full time

Job summary

Cyient is seeking a Senior Embedded AI Platform Engineer to design and scale AI solutions that transform embedded software development. This role requires proficiency in Embedded C, RTOS, and Python, with hands-on experience in developing multi-agent systems. The ideal candidate will have 5+ years of software engineering experience and 2+ years with LLM-based AI solutions, contributing to projects that enhance developer productivity across various domains, including safety-critical industries.

Qualifications

• 5+ years of software engineering experience.
• 2+ years of hands-on experience with LLM-based systems, generative AI, or agentic AI.
• Familiarity with real-time operating systems (RTOS) concepts.

Responsibilities

• Design, build, and deploy multi-agent AI systems that automate software development workflows.
• Architect and implement RAG pipelines, knowledge graphs, and vector database solutions.
• Build enterprise integrations that connect AI agents with development tools.

Skills

Embedded C

RTOS

C++ code understanding

Python

Multi-agent development

Education

Bachelor's or Master's degree in Computer Science, Software Engineering, AI/ML

Tools

MATLAB/Simulink

GitHub Copilot

AWS Bedrock

Job description

Senior Embedded AI Platform Engineers to design, build, and scale AI agents and AI-powered developer tools that transform how embedded software is developed, tested, and shipped.

Resource will work at the intersection of Generative AI, agentic AI systems, and embedded software engineering—building AI solutions that understand the complexity of multi-ECU architectures, real-time operating systems, safety-critical code, and industrial communication protocols.

Must have skills

Embedded C, RTOS, & C++ code understanding, Multi agent development hands on experience in Python; Orchestration experience.

What resource will Do

• Understand existing code based of Embedded Systems with RTOS
• Design, build, and deploy multi-agent AI systems that automate software development workflows
• Build context engineering frameworks that enable AI models to produce domain-specific, production-grade output for embedded software
• Architect and implement RAG pipelines, knowledge graphs, and vector database solutions to give AI agents access to large-scale domain knowledge
• Build enterprise integrations that connect AI agents with development tools (GitHub, Azure DevOps, CI/CD pipelines, test management systems)
• Design automated quality gates and validation agents that ensure AI-generated output meets coding standards, safety compliance, and architecture guidelines
• Build observability, metrics, and evaluation frameworks to measure AI impact on productivity, quality, and cost
• Develop full-stack tooling (VS Code extensions, web dashboards, CLI tools) that deliver AI capabilities to engineering teams

What resource can Bring

• Embedded Software Domain Understanding
• Understanding of embedded software development workflows and toolchains
• Familiarity with C/C++ development for embedded systems
• Understanding of testing frameworks and methodologies: GTest, pytest, MIL, SIL, HIL
• Familiarity with real-time operating systems (RTOS) concepts
• Understanding of industrial communication protocols (CAN, J1939, Ethernet)
• Exposure to model-based software development (MATLAB/Simulink) is a plus
• Exposure to QT framework and UI development for embedded displays is a plus
• GenAI & Agentic AI Expertise
• Context engineering — designing and structuring domain context to maximize LLM output quality
• Familiarity with AI-native development tools: GitHub Copilot, Cursor, Windsurf, Antigravity
• LLM-based system architecture (OpenAI, Anthropic, open-source LLMs)
• Multi-agent orchestration and tool-integrated agents
• Retrieval-Augmented Generation (RAG) pipelines
• Vector databases (Pinecone, Weaviate, ChromaDB, pgvector, or equivalent)
• Agent frameworks (LangChain, LangGraph, CrewAI, AutoGen, or equivalent)
• AWS Bedrock, SageMaker, and cloud-agnostic AI architectures
• LLMOps, evaluation frameworks, observability, and guardrails
• Prompt engineering, structured outputs, and function calling
• AI governance, security, and responsible AI design
• Custom & Offline AI Solutions
• On-premise and air-gapped LLM deployments
• Local and embedded AI agents for controlled environments
• Quantized models (GGUF, ONNX) and optimized inference pipelines
• Fine-tuning, domain adaptation, and hybrid AI architectures
• Full-Stack Development
• Python
• VS Code extension development or IDE tooling experience
• REST APIs, WebSocket, and modern web application frameworks

Preferred Qualifications

• 5+ years of software engineering experience
• 2+ years of hands-on experience with LLM-based systems, generative AI, or agentic AI
• Experience building AI solutions for engineering or developer productivity use cases
• Experience in regulated or safety-critical industries (automotive, agriculture, aerospace, medical) is a strong plus
• Bachelor's or Master's degree in Computer Science, Software Engineering, AI/ML, or related field