Job Description

Job Summary

• 10+ years of enterprise software engineering experience with bachelor’s or master’s degree in computer science, Software Engineering, or a related technical discipline
• Experience in solution architecture and SDLC transformation initiatives

Key Responsibilities

Generative AI & Agent Technologies (2+ Years)

• Hands-on experience building GenAI Agent systems using LangChain, LangGraph, CrewAI, AutoGen, MCP Protocol.
• Strong knowledge of LLM APIs: Anthropic Claude, OpenAI GPT-4o
• Experience implementing Retrieval-Augmented Generation (RAG) pipelines and vector stores (Pinecone, Weaviate, pgvector, Chroma)
• Proficiency in prompt engineering techniques: Chain-of-Thought, ReAct, few-shot/zero-shot strategies
• Exposure to cloud AI platforms: AWS Bedrock, Azure OpenAI Service, or Google Vertex AI

CI/CD & DevOps Tooling

• Extensive hands-on experience with Jenkins — pipeline-as-code (Jenkinsfile), multi-branch pipelines, shared libraries, and plugin management
• Additional CI/CD experience with GitHub Actions, GitLab CI, or AWS CodePipeline / CodeBuild for end-to-end delivery automation
• Containerisation and orchestration: Docker, Kubernetes (EKS / self-managed), Helm charts, and service mesh (Istio or AWS App Mesh)
• Infrastructure-as-Code: Terraform, AWS CloudFormation, or AWS CDK for provisioning and managing cloud resources
• Configuration management and automation: Ansible, Chef, or AWS Systems Manager (SSM) for environment consistency
• Observability and monitoring: AWS CloudWatch, Prometheus, Grafana, ELK Stack (Elasticsearch, Logstash, Kibana), and distributed tracing with AWS X-Ray or Jaeger

AWS Cloud Platform

• Core AWS services: EC2, ECS/EKS, Lambda, S3, RDS, DynamoDB, VPC, IAM, and CloudFront
• AI/ML services: AWS Bedrock (foundation model hosting & RAG), SageMaker (model training, endpoints, pipelines), and Bedrock Agents for agentic workflows
• Secrets and security: AWS Secrets Manager, KMS, IAM roles/policies, SCPs, and security best practices for LLM workloads
• Cost optimisation: AWS Cost Explorer, tagging strategies, reserved/spot instances, and FinOps practices for AI workloads

Solution Architecture & SDLC Transformation

• Demonstrated experience leading architecture reviews, technical road-mapping, and design-pattern governance
• Ability to transform traditional SDLC processes with AI-assisted development, automated testing, and DevSecOps practices

Domain Experience

• Experience in the life insurance domain: underwriting, claims processing, policy administration, or actuarial tooling
• Knowledge of insurance regulatory and data-governance standards (SOX, GDPR equivalents)

Skill Requirements

Soft Skills & Professional Competencies

• Excellent written communication skills — ability to produce clear technical documents, architecture proposals, and executive summaries tailored to both technical and non-technical audiences
• Strong verbal communication — able to articulate complex AI/engineering concepts confidently in meetings, workshops, and presentations
• Stakeholder engagement — proven ability to work closely with business leaders, product owners, and cross-functional teams to align technical solutions with business goals
• Collaborative team player — comfortable working in distributed, agile teams while also being self-driven as an individual contributor
• Mentoring & knowledge sharing — willingness to coach junior engineers and contribute to a culture of continuous learning
• Analytical thinking — structured problem-solver who can break down ambiguous challenges and propose pragmatic, scalable solutions
• Adaptability — thrives in fast-moving environments where AI technologies and business priorities evolve rapidly

Other Requirements

1.DevOps Engineer Expert certification is preferred.