Explicitly requires vibe coding skills; uses AI code assistants (GitHub Copilot, Gemini, Claude) and agentic frameworks to accelerate development.
About the Role
Lead and mentor a team to architect, build, and deploy production-scale, cloud-native AI agents and services on Google Cloud Platform, using agentic frameworks and AI code-assist tools to accelerate development. Drive MLOps, observability, and modern microservices practices to deliver reliable, scalable APIs and platforms.
Job Description
Role
Senior AI Engineer responsible for technical vision and execution of cloud-native, production-grade AI systems. Lead a cross-functional team to design, implement, and operate agentic AI solutions, scalable APIs, microservices, and PaaS/SaaS platforms on Google Cloud Platform.
Key Responsibilities
- Design, build, and deploy complex AI agents using LangChain and LangGraph.
- Design, test, and refine prompts and contextual data frameworks (prompt & context engineering).
- Research, prototype, and integrate foundation models, RAG techniques, and agentic frameworks.
- Engineer and operate scalable AI systems in production on Google Cloud Platform (GCP).
- Establish MLOps best practices for agentic systems, including reliability, versioning, monitoring, and observability (e.g., Langfuse).
- Use AI code-assist tools (Gemini, GitHub Copilot, Claude) to accelerate development, documentation, testing, and monitoring.
- Build, manage, and mentor a team of software, quality, and reliability engineers.
- Define and report engineering metrics (SLA, SLO, SLI) and enforce DevSecOps and FinOps practices.
- Collaborate with product managers, architects, SREs, and business stakeholders to define strategy and roadmaps.
- Lead troubleshooting and incident resolution; participate in agile ceremonies and produce technical documentation and run books.
Requirements
- Bachelor’s degree or equivalent experience.
- 5+ years in software engineering with strong technical leadership and delivery of scalable systems.
- 1+ years in a dedicated AI/ML role with hands-on model integration and MLOps experience.
- 1+ years architecting and building with LangChain, LangGraph, or similar agentic AI frameworks.
- 2+ years working with Google Cloud Platform AI/ML services (e.g., Vertex AI).
- 3+ years of experience with Kubernetes workloads.
- Proficiency in Python, JavaScript/TypeScript and/or Java; working knowledge of a modern front-end framework (Angular, React, or Vue).
- Experience with LLM observability tools such as Langfuse.
- Cloud-native skills: Docker, Kubernetes, IaC (Terraform or CloudFormation), CI/CD (GitHub Actions, Argo CD, Jenkins).
- Database experience with both SQL (Spanned DB, Alloy DB, PostgreSQL, MySQL) and NoSQL (MongoDB, DynamoDB, Firestore).
- Strong problem-solving, communication, mentoring, and metrics-driven mindset.
Nice-to-have
- Hands-on experience with Generative AI models (Gemini, ChatGPT, Claude, Llama).
- Experience creating and deploying AI agents to production environments.
- Familiarity with DevSecOps and FinOps practices.
Benefits
- Hybrid work setting.
- Comprehensive compensation and healthcare packages.
- Paid time off.
- Organizational growth and online learning platform with guided career tracks.
Location
- Primary location: Pune, India. Hybrid work arrangement.