AI Lead

Role Overview

As an AI Lead, you will architect, build, and deliver cutting-edge GenAI and agentic systems that power enterprise and product workflows. This role blends deep technical expertise in backend engineering, cloud-native development, and modern AI/ML with the ability to design scalable AI architectures, lead engineering execution, and collaborate cross-functionally with product and business stakeholders. You will drive end-to-end solution design from ingestion, orchestration, and retrieval to model selection, evaluation, and production deployment.

Key Responsibilities

• GenAI & Agentic Architecture Design
  • Design end-to-end GenAI architectures: multi-agent workflows, tool orchestration, memory systems, RAG pipelines, and long-running workflows.
  • Translate business problems into technical AI solution blueprints (models, tools, data flows, integrations).
  • Define standards and best practices for:
  • Prompt engineering
  • Tool-calling architecture
  • Context management
  • Retrieval strategies
  • Multi-agent orchestration
• Backend & Microservices Development
  • Implement Python/FastAPI microservices and serverless components (AWS Lambda, Azure Functions), with containerized workloads on Kubernetes (EKS/AKS/GKE).
  • Define API contracts and integration patterns between agents, microservices, and external systems.
  • Develop ETL/ELT pipelines using Python/SQL for structured & unstructured data across data lakes/warehouses (S3, ADLS, Cosmos DB, BigQuery, SQL DB).
  • Ensure services meet non-functional requirements: scalability, performance, latency, and cost efficiency.
• Retrieval & Knowledge Systems
  • Architect retrieval pipelines using vector databases: Qdrant, Weaviate, Chroma, PGVector.
  • Design embedding, indexing, chunking, and hybrid retrieval strategies.
  • Optimize RAG flows for enterprise-grade reliability and accuracy.
• Evaluation, Governance & Safety
  • Establish evaluation frameworks: offline/online tests, A/B experiments, human-in-the-loop feedback loops.
  • Implement guardrails: input/output safety, content filters, hallucination detection.
  • Ensure compliance with data security, privacy, access control, and safe AI principles.
• Leadership, Collaboration & Delivery
  • Serve as a technical leader across engineering squads-providing mentorship, code reviews, and design guidance.
  • Partner with product managers, customers, and cross-functional teams to define requirements, scope, and architectural decisions.
  • Lead architecture reviews, maintain decision records, and deliver technical documentation.
  • Represent the AI team in customer meetings, proposals, and solution walkthroughs.

Required Skills & ExperienceTechnical Expertise

• 6+ years in software/solution architecture or backend engineering.
• 2+ years hands-on building GenAI/ AgenticAI/ LLM systems.

Strong proficiency in:

• Python (OOP, async, API development)
• Cloud (AWS required; Azure/GCP is a plus)
• FastAPI, serverless functions (Lambda/Azure Functions)
• Docker, Kubernetes, container orchestration

Strong understanding of:

• LLMs, embeddings, prompt engineering
• Tool-calling, multi-agent patterns
• RAG design, vector search, chunking strategies
• Experience with vector databases (Qdrant, Weaviate, PGVector, Chroma)
• Solid knowledge of SQL & Python ETL for data engineering

Hands-on experience with:

• AWS services (S3, Lambda, API Gateway, EventBridge, DynamoDB/RDS)
• Azure services (ADLS, Cosmos DB, Azure SQL)
• CI/CD automation and Git workflows
• Fundamental front-end knowledge (React/Angular/HTML/CSS) for collaboration

Engineering Practices

• Strong unit/integration testing discipline.
• Experience with IaC (Terraform/CloudFormation/ARM).
• Strong understanding of cloud-native observability (logging, metrics, tracing).
• Experience running systems in Agile squads with Jira or similar tools.

Soft Skills & Leadership

• Excellent communication-capable of simplifying complex AI concepts.
• Strong ownership, product mindset, and customer-facing confidence.
• Ability to balance rapid experimentation with production reliability.
• Comfortable leading architecture discussions and mentoring engineers.

Preferred Qualifications

• Experience contributing to open-source projects or AI/ML communities.
• Cloud certifications (AWS Developer Associate, Azure Developer, GCP Cloud Developer) are plus.
• Experience with data governance, enterprise security, and compliance frameworks.
• Exposure to agentic AI platforms/ Frameworks (e.g., LangChain, langgraph, Autogen, Haystack, OpenAI's MCP etc).
• Contributions to advanced RAG systems or prompt engineering frameworks.