Lead AI Solution Engineer

Job Description: Lead AI Solution Engineer

Role Overview
As a Lead AI Solution Engineer, you will serve as both the technical architect and the primary builder for our next-generation AI solutions. You will transform ambitious AI concepts into robust, production-ready systems, bridging the gap between cutting-edge LLM research and enterprise-grade software engineering. You will own the full lifecycle of AI applications—from initial architectural design and agentic workflow development to building secure, observable, and highly scalable production environments using modern DevOps practices.

Key Responsibilities

• Architectural Leadership: Design and implement resilient system architectures for AI applications, including multi-agent orchestration, RAG pipelines, and event-driven backends.
• AI Development & Orchestration: Lead the development of sophisticated GenAI applications using frameworks like LangChain, LangGraph, or AutoGen. Implement Agent-to-Agent (A2A) workflows and Model Context Protocol (MCP) integrations.
• Production Engineering (DevOps & IaC): Architect and maintain infrastructure using Infrastructure as Code (e.g., Terraform, CDK). Establish and optimize robust CI/CD pipelines to ensure rapid, secure deployment cycles.
• Observability & Reliability: Implement comprehensive monitoring, logging, and tracing solutions. Utilize tools like Datadog (or similar stacks like New Relic/ELK) to monitor LLM performance, latency, token usage, and system health in real-time.
• Security & Identity: Architect secure API integrations, implementing robust authentication/authorization protocols (OAuth 2.0, OpenID Connect, JWT) to ensure strict data privacy and compliance.
• Technical Excellence: Drive coding standards, conduct architectural and code reviews, and mentor team members on software design principles (SOLID), cloud architecture, and AI integration best practices.
• Strategy & Evaluation: Partner with stakeholders to define model evaluation protocols (A/B testing, statistical analysis) and ensure high-quality, cost-effective LLM performance.

Required Skills and Experience

• Engineering Foundation: 7+ years of software engineering experience with a deep understanding of design patterns, clean architecture, and distributed systems.
• AI/ML Expertise:
• Hands-on experience integrating LLMs into production applications.
• Proficiency in orchestration frameworks (LangChain, LangGraph, PydanticAI, etc.).
• Deep understanding of RAG architectures, vector databases (e.g., Pinecone, Milvus), and prompt engineering.
• Backend Mastery: Expert-level proficiency in Python (FastAPI/Flask). Strong experience building RESTful and async, event-driven architectures (message queues/event buses).
• DevOps & Infrastructure:
• IaC: Proven experience with Terraform, AWS CloudFormation, or Pulumi.
• CI/CD: Experience building production-grade deployment pipelines.
• Cloud: Hands-on experience with major cloud platforms (AWS, Azure, or Google Cloud Platform).
• Observability: Practical experience configuring and maintaining monitoring stacks (Datadog, Grafana, Prometheus) to track application performance, errors, and LLM-specific telemetry (cost/latency).
• Security: Strong background in secure API development, including implementing and managing OAuth 2.0 and mTLS.
• Leadership: Demonstrated ability to lead technical initiatives, mentor engineers, and communicate complex trade-offs to non-technical stakeholders.

Preferred Qualifications

• Familiarity with container orchestration (Docker/Kubernetes).
• Experience building Agentic AI systems with autonomous decision-making capabilities.
• Experience in a regulated industry (Legal, Fintech, or Healthcare) and associated compliance/data privacy requirements.
• Understanding of the internal scaling, limitations, and fine-tuning of Transformer models.