We are seeking a highly experienced Principal Engineer to own the technical direction of our enterprise backend platforms and to lead the applied development of agentic AI solutions. The core of this role is strong backend and platform engineering in Node.js and TypeScript: designing, building, and operating reliable, scalable services that enterprise workloads depend on. Alongside this, you will apply agentic AI as a strategic differentiator, building
production-grade agent workflows that automate documentation, knowledge-management, and enterprise productivity processes.
As a Principal Engineer, you will set architecture standards, make high-impact technical decisions, and raise engineering maturity across teams. You are expected to combine deep hands-on backend expertise with practical, production-minded application of agentic AI, keeping innovation grounded in delivery, reliability, security, and maintainability.
- Hold technical ownership of backend platforms and services built on Node.js and TypeScript, from architecture through production operation.
- Set engineering standards for Node.js and TypeScript, driving code quality, maintainability, and consistency across teams.
- Design clean, well-versioned APIs, microservices, and event-driven architectures for enterprise-scale workloads.
- Architect distributed systems with clear attention to scalability, reliability, security, and data modeling.
- Own production readiness: performance validation, capacity planning, observability, and operational ownership of live services.
- Lead cloud-native and hybrid deployments (AWS/GCP/On-Prem) with containerized, automated delivery.
- Design agent workflows that automate documentation, knowledge-management, and enterprise productivity processes.
- Build RAG-based workflows and tool/function-calling integrations that connect agents to enterprise platforms.
- Apply planner / executor / reviewer (critic) patterns with human-in-the-loop checkpoints for high-stakes steps.
- Engineer safe tool execution, fallback handling, and workflow failure recovery so automations degrade gracefully.
- Ensure auditability of agent actions and partner with the documentation team to turn automation opportunities into working solutions.
- Establish tracing, evaluation, prompt and version management, and regression testing for agent workflows.
- Monitor production agent workflows for cost, latency, quality, and failures, and drive improvements from that data.
- Apply practical AI controls: prompt injection mitigation, sensitive-data leakage prevention, least-privilege tool access and permissioning, audit logs, role-based access, and human approval flows.
- Define evaluation practice using evaluation datasets and golden test cases, RAG quality and groundedness checks, task success rate, and human feedback loops to reduce hallucination risk.
- Evaluate and introduce emerging technologies, frameworks, and AI tooling where they add clear value.
- Perform technical design reviews, code reviews, and solution validations for critical projects.
- Influence technology roadmaps and align engineering outcomes with organizational goals.
- Mentor, coach, and develop senior engineers, fostering a culture of technical excellence and innovation.
- Influences engineering strategy and architecture decisions across teams, not just within a single project.
- Mentors and develops senior engineers and tech leads, raising overall engineering maturity.
- Provides technical governance, setting standards and guardrails that teams can follow with confidence.
- Exercises cross-team influence and aligns stakeholders around sound technical direction.
- Balances innovation with delivery, risk, security, and maintainability in every major decision.
- Communicates complex trade-offs clearly to both technical and business audiences.
- 12+ years in software engineering with deep, hands-on backend expertise in Node.js and TypeScript.
- Strong backend architecture skills: REST API design, microservices, event-driven systems, and data modeling.
- Solid experience with distributed systems, concurrency, caching, and messaging (Kafka, PubSub etc.).
- Strong system design capability and fluency with design patterns and architecture blueprints.
- Experience with cloud-native / hybrid architectures (AWS, GCP, On-Prem) and enterprise integrations.
- DevOps and CI/CD practices with containerization (Docker, Kubernetes, Helm).
- Solid knowledge of databases (RDBMS: PostgreSQL/MSSQL, NoSQL: Redis/ElasticSearch).
- Strong exposure to observability tools (OpenTelemetry, Prometheus, ELK, Grafana).
- Practical, hands-on exposure to building agentic AI or LLM-based workflows, including RAG and tool/function calling.
- Familiarity with one or more agent frameworks (e.g. LangGraph, Semantic Kernel, OpenAI Agents SDK, Amazon Bedrock Agents, Google ADK, CrewAI, AutoGen).
- Experience with vector databases and LLM evaluation or tracing tools.
- Working knowledge of Python, given its role in the AI tooling ecosystem.
- Bachelor's/Master's degree in Computer Science, Engineering, or related field.
- 12–16 years of professional experience, including significant leadership responsibilities.
- Proven track record as a Principal Engineer / Senior Architect / Technology Leader in enterprise-grade software systems.
- Excellent communication, analytical, and problem-solving skills.
