Principle Ai Engineer

BMW TechWorks India Private Limited; India; On-site; INR 2,000,000 - 3,000,000; Full time

Job summary

BMW TechWorks India Private Limited is seeking an AI Expert to lead the implementation of Agentic AI across the Software Development Lifecycle. The candidate will develop AI agents to enhance engineering productivity and quality across the organization.

You should bring strong technical leadership skills and a deep understanding of end-to-end software development processes. A hands-on approach and experience with Generative AI or LLM solutions are essential for this role.

Qualifications

• Strong experience in software engineering, solution architecture, or engineering productivity.
• Proven experience building AI solutions, especially in Generative AI.
• Ability to translate engineering problems into AI-enabled solutions.

Responsibilities

• Define and implement the technology roadmap for AI adoption.
• Design and build enterprise-grade AI agents.
• Work with engineering teams to implement AI-driven workflows.

Skills

AI engineering capability

Strong problem-solving capability

Technical leadership skills

Problem-solving

Education

Degree in relevant field

Tools

Azure OpenAI

GitHub

Docker

Kubernetes

Job description

Travel Flexibility

Flexibility to travel for business trips.

Experience

12 to 15 Years of experience.

Job Profile

We are looking for a highly hands‑on AI Expert who can lead the technology implementation of Agentic AI across the Software Development Lifecycle. This role is expected to combine deep engineering capability with technical steering experience to help the organization adopt AI‑driven software delivery practices at a scale.

You will be responsible for designing, building, integrating, and operationalizing AI agents that improve engineering productivity, software quality, automation, and delivery speed across the company.

Key Responsibilities

• Define and implement the technology roadmap for Agentic AI adoption across SDLC workflows.
• Design and build enterprise‑grade AI agents for software engineering use cases such as:
  • Requirement analysis and backlog refinement
  • User story and acceptance criteria generation
  • Solution design assistance
  • Code generation and refactoring
  • Code review automation
  • Unit test and test case generation
  • Defect triaging and root cause analysis
  • CI/CD pipeline assistance
  • Release readiness assessment
  • Production incident analysis
  • Technical documentation generation
• Work hands‑on with engineering teams to identify, prototype, validate, and scale AI‑driven SDLC use cases.
• Architect and implement reusable Agentic AI frameworks, accelerators, templates, and reference implementations.
• Build multi‑agent workflows that can reason, plan, use tools, call APIs, access repositories, analyze logs, and assist engineers in day‑to‑day delivery activities.
• Integrate AI agents with core engineering platforms such as:
  • GitHub, GitLab, Azure DevOps, Bitbucket
  • Jira, Confluence, ServiceNow
  • CI/CD pipelines
  • IDEs and developer portals
  • Code quality and security scanning tools
  • Test automation frameworks
  • Observability and monitoring platforms
• Provide technical steering to feature engineering teams on AI architecture, agent design, prompt engineering, orchestration patterns, and implementation best practices.
• Evaluate and select LLMs, agent frameworks, vector databases, orchestration tools, and AI development platforms based on enterprise needs.
• Agent orchestration
• Context management
• RAG implementation
• Human‑in‑the‑loop approvals
• AI observability
• Build secure and scalable AI solutions that comply with enterprise security, data privacy, and responsible AI requirements.
• Define and implement guardrails to prevent hallucination, data leakage, insecure code generation, prompt injection, and unauthorized tool execution.
• Design evaluation mechanisms to measure the accuracy, usefulness, reliability, safety, and business value of AI agents.
• Steer technical communities, architecture forums, and engineering guilds to accelerate AI adoption across teams.
• Coach and mentor developers, architects, DevOps engineers, and QA teams on practical AI engineering patterns.
• Partner with engineering leadership to measure adoption and impact through metrics such as:
  • Developer productivity improvement
  • Code review cycle‑time reduction
  • Defect reduction
  • Test coverage improvement
  • Deployment frequency improvement
  • Incident resolution time reduction
  • Engineering effort savings
• Stay current with emerging Agentic AI, LLMOps, AI engineering, and developer productivity technologies, and translate them into practical enterprise solutions.

What Should You Bring Along?

You should bring strong hands‑on AI engineering capability, practical SDLC knowledge, and the ability to steer technology implementation across multiple engineering teams.

Ideal Candidate

• Strong experience in software engineering, solution architecture, platform engineering, DevOps, or engineering productivity.
• Proven hands‑on experience building Generative AI, LLM‑based, or Agentic AI solutions.
• Deep understanding of end‑to‑end SDLC workflows, including requirements, design, development, testing, deployment, operations, and support.
• Ability to translate engineering pain points into practical AI‑enabled solutions.
• Strong technical leadership skills with experience steering architecture, engineering standards, and implementation practices.
• Experience taking AI solutions from proof of concept to production‑grade implementation.
• Strong problem‑solving capability and willingness to work hands‑on with code, APIs, tools, pipelines, and cloud platforms.
• Ability to work with engineering teams, architects, security teams, DevOps teams, QA teams, product owners, and senior leadership.
• Strong understanding of enterprise technology landscapes and how AI can be safely embedded into existing workflows.
• Ability to define reusable patterns and platforms rather than isolated one‑off solutions.
• Good communication skills with the ability to explain technical AI concepts to engineering and leadership audiences.
• Strong ownership mindset with the ability to drive adoption, resolve technical blockers, and influence engineering teams.

Must Have Technical Skill

• AI, GenAI, and Agentic AI
  • Strong understanding of Large Language Models, Generative AI, Agentic AI, and AI‑assisted software engineering.
  • Hands‑on experience with one or more LLM platforms such as:
    • Azure OpenAI
    • OpenAI APIs
    • AWS Bedrock
    • Google Gemini
    • Anthropic Claude
    • Open‑source LLMs
  • Hands‑on experience with agentic AI frameworks such as:
    • LangChain
    • LangGraph
    • Microsoft Semantic Kernel
    • AutoGen
    • CrewAI
    • LlamaIndex
  • Experience designing and implementing AI agents with:
    • Planning and reasoning
    • Tool usage
    • Function calling
    • Memory
    • Context management
    • Multi‑step execution
    • Human‑in‑the‑loop approval
    • Agent‑to‑agent collaboration
  • Strong prompt engineering and system prompt design experience.
  • Experience with Retrieval‑Augmented Generation using enterprise knowledge sources.
  • Experience with embeddings, vector search, semantic search, and knowledge grounding.
  • Ability to evaluate LLM and agent outputs using accuracy, relevance, consistency, safety, and performance metrics.
• SDLC Automation and Developer Productivity
  • Strong understanding of software development, lifecycle processes and engineering workflows.
  • Experience implementing automation across SDLC areas such as:
  • Requirement analysis
  • Development
  • Code review
  • Testing
  • Build and deployment
  • Release management
  • Incident management
  • Hands‑on experience integrating AI solutions with engineering tools such as:
  • GitHub
  • GitLab
  • Azure DevOps
  • Bitbucket
  • Jira
  • Confluence
  • Experience with CI/CD tools and release automation.
  • Understanding of code quality, code review, static analysis, secure coding, and software testing practices.
  • Ability to design AI agents that interact with repositories, tickets, documentation, pipelines, APIs, and logs.
• Programming and Engineering
  • Strong programming experience in at least one or more languages:
    • Python
    • Java
    • JavaScript / TypeScript
    • C#
    • Go
  • Ability to build production‑grade APIs, backend services, automation scripts, and integration components.
  • Experience with REST APIs, event‑driven integration, webhooks, and service‑to‑service communication.
  • Strong knowledge of software design principles, design patterns, clean code, and modular architecture.
  • Experience working with databases, structured data, unstructured data, and enterprise knowledge repositories.
• Cloud, Platform, and Architecture
  • Strong experience with at least one major cloud platform:
    • Microsoft Azure
    • AWS
    • Google Cloud Platform
  • Experience designing scalable, secure, and maintainable AI solution architectures.
  • Understanding of cloud‑native development, microservices, containers, and API‑based architectures.
  • Hands‑on experience with Docker and good understanding of Kubernetes or container orchestration.
  • Experience with enterprise authentication and authorization patterns such as OAuth, OpenID Connect, managed identities, service principals, and role‑based access control.
• LLMOps, Observability, and Governance
  • Understanding of LLMOps or AI application lifecycle management.
  • Experience implementing monitoring and observability for AI solutions, including:
  • Prompt tracing
  • Agent execution tracking
  • Token consumption monitoring
  • Latency monitoring
  • Error handling
  • Cost monitoring
  • Output quality measurement
  • Experience implementing AI guardrails, input/output validation, and policy checks.
  • Understanding of risks such as:
  • Hallucination
  • Prompt injection
  • Data leakage
  • Insecure code generation
  • Bias
  • Unauthorized tool execution
  • Knowledge of responsible AI, data privacy, security, and enterprise compliance requirements.

Good to Have Technical Skills

• Experience with GitHub Copilot, GitHub Copilot Enterprise, Microsoft Copilot Studio, or enterprise AI assistant platforms.
• Experience implementing AI‑assisted development practices across large engineering organizations.
• Knowledge of Model Context Protocol, AI tool calling standards, and agent interoperability patterns.
• Experience with vector databases and search platforms such as:
• Pinecone
• Weaviate
• Milvus
• Chroma
• FAISS
• Elasticsearch / OpenSearch
• Experience with AI evaluation frameworks and test harnesses for LLM applications.
• Experience with tools such as LangSmith, PromptFlow, OpenTelemetry, Arize, TruLens, or similar AI observability platforms.
• Experience with DevSecOps and secure SDLC implementation.
• Knowledge of code analysis and security tools such as:
• SonarQube
• Checkmarx
• Veracode
• GitHub Advanced Security
• Experience with test automation frameworks such as:
• Selenium
• Playwright
• Cypress
• JUnit
• PyTest
• Postman
• Experience with AIOps, incident automation, log analytics, and observability platforms such as:
• Dynatrace
• Splunk
• New Relic
• Experience building internal developer platforms, developer portals, or engineering productivity platforms.
• Familiarity with Backstage or similar internal developer portal frameworks.
• Experience with knowledge platforms such as SharePoint, Confluence, ServiceNow Knowledge Base, or enterprise document repositories.
• Exposure to model fine‑tuning, model distillation, synthetic data generation, or domain adaptation.
• Experience with enterprise architecture, governance and technology steering forums.
• Cloud, AI, architecture, or security certifications would be an advantage.