Engineering Lead

Job Title: Engineering Lead for Building enterprise scale Gen AI Platform

Location:

Job Summary:

Solution Architect

Key Responsibilities:

• Architect end-to-end GenAI solutions using

  LLMs (e.g., OpenAI, Deepseek, Llama)

  for a variety of enterprise use cases including summarization, semantic search, chat agents, and workflow automation.
• Translate business requirements into scalable

  LLM-enabled software architectures

  balancing functional needs with performance, cost, compliance, and user experience requirements.

• Own full-stack solution delivery

  — from UX/UI design to backend services, data integrations, and LLM orchestration — ensuring cohesive user experiences and seamless data flow across layers.
• Guide development teams on

  prompt engineering

  ,

  RAG (retrieval-augmented generation)

  , and

  LLMOps best practices

  .

• Implement robust workflow orchestration

  for GenAI use cases using tools like Temporal, Airflow, or custom orchestrators to support multi-agent workflows and business logic execution.
• [RT1] [RT2] Establish secure and compliant LLM pipelines, ensuring adherence to data protection, PII masking, auditability, and enterprise governance policies.
• Stay abreast of emerging GenAI tools, frameworks, and trends to continuously improve solution design.

• Lead application development lifecycle

  : define branching strategies, enforce CI/CD practices, and implement automated quality gates (tests, linting, security scans). Architect and implement

  self-service internal platforms

  for build, test, deployment, and monitoring.

• Drive engineering best practices

  including clean code, modularization, reusable component libraries, design patterns for GenAI, and consistent coding standards across teams.
• Maintain architectural oversight across environments, collaborating with DevOps and SRE teams to provision infrastructure using IaC tools (e.g., Terraform, Bicep, Pulumi) and to implement monitoring, logging, and tracing for resilient, observable GenAI platforms.

Required Skills:

• Frontend:

  React.js, Next.js, or similar frameworks.

• Backend:

  Python, Node.js, FastAPI, Flask, Express.js.

• GenAI Stack:

  LangChain, LlamaIndex, OpenAI APIs.

• Cloud Platforms:

  Azure or GCP (LLM deployments, Kubernetes, serverless functions).

• Database:

  PostgreSQL, familiarity with vector databases.

• Containerization & Orchestration:

  Docker, Kubernetes, Helm, EKS/GKE/AKS

• CI/CD:

  GitHub Actions, Jenkins, ArgoCD, FluxCD

• Developer Enablement:

  Backstage, Internal Dev Portals, Platform APIs
• Experience designing and integrating

  LLMOps pipelines

  , prompt templating, and caching strategies.
• Excellent understanding of

  API architecture

  (REST, GraphQL).
• Proven experience in

  agile development methodologies

  .

Preferred Qualifications:

• Experience working with enterprise-scale product or application development, rollout and adoption
• Hands-on experience with GenAI solution building blocks, LLM fine-tuning, custom embeddings, or proprietary data integration.
• Contributions to open-source AI/NLP projects or participation in GenAI communities.
• Exposure to evaluation frameworks for LLM outputs (toxicity, accuracy, hallucination detection).
• Proven expertise in

  building internal platforms or PaaS environments

  .
• Strong understanding of

  software engineering practices

  , microservices, and distributed systems.
• Passion for

  automation, standardization, and developer experience

  .