AI FIRST – Principal Engineer

Tamil Nadu (Remote) – Full-time (40 hrs/week)

Experience: 8–10 Years

Job Description

We’re looking for a Principal Engineer to serve as a technical anchor for our AI-first engineering organization. In this role, you’ll drive the architecture and technical direction of our most complex systems, define engineering standards across the team, and ensure our AI-powered products are built to scale. You’ll work closely with the Tech Lead and senior stakeholders to translate business goals into robust, forward-thinking technical solutions — while also being deeply hands-on when it matters.

Key Responsibilities

Full Stack Development

• Lead the technical design of large-scale, cross-cutting full-stack initiatives.

• Define and enforce engineering standards, patterns, and best practices across teams.

• Implement full-stack features using React.js, Next.js, and TypeScript on the frontend, with Python (FastAPI) and/or Node.js backends.

• Architect and oversee microservices, APIs, and service integration strategies.

• Own and evolve AWS-based infrastructure for web and backend workloads, using Terraform for infrastructure as code.

• Lead containerization and orchestration strategy using Docker and Kubernetes.

• Drive system reliability, security architecture, and cost optimization across services.

• Size and estimate projects across full-stack and AI workstreams; guide planning and prioritization.

• Operate within an Agile delivery model, using Jira for planning and cross-team coordination.

• Mentor senior and mid-level engineers; champion high engineering standards through code and design reviews.

AI Engineering

• Set the technical direction for GenAI development, including model selection, pipeline architecture, and scalability strategy.

• Define and own best practices for LLM development, evaluation, and production deployment.

• Architect end-to-end LLM pipelines from experimentation to production, including RAG systems and retrieval infrastructure.

• Develop and standardize advanced prompt engineering frameworks across the team.

• Lead rigorous model evaluations and define performance optimization strategies.

• Design and oversee CI/CD pipelines tailored for AI systems.

• Architect and maintain AWS-based infrastructure for AI workloads (SageMaker, etc.).

• Build and evolve monitoring, observability, and evaluation tooling for LLM applications.

Candidate Requirements

• 8–10 years of software engineering experience, including meaningful time in senior or lead roles.

• Deep full-stack development expertise using React.js, Next.js, and TypeScript.

• Strong proficiency in Python (FastAPI) and/or Node.js for backend services.

• Proven track record of building and deploying LLM or GenAI applications in production at scale.

• Deep understanding of prompt engineering, LLM evaluation, and RAG systems.

• Expert-level knowledge of AWS (SageMaker, Lambda, ECS, S3, etc.), Docker, and Kubernetes.

• Strong experience with Terraform and CI/CD pipelines (GitHub Actions or similar).

• Excellent background in system design, API architecture, distributed systems, and microservices.

• Experience driving engineering standards, cross-team alignment, and technical decision-making.

• Strong communication skills — able to influence technical direction with peers and leadership.

Good to Have

• Experience with fine-tuning, RLHF, or training LLMs.

• Familiarity with LangChain, LlamaIndex, or similar frameworks.

• Background in MLOps, model monitoring, and AI observability.

• Experience with A/B testing and experimentation frameworks.

• Open-source contributions or thought leadership in GenAI or distributed systems.