Associate Platform and Data Engineer

Reporting to Head, Platforms and Data Engineering, the Platforms and Data Engineer will work closely with Data Scientists, Threat/Malware Researchers, Project Managers and Infrastructure Engineers to develop and manage AI-powered agentic systems and data engineering solutions. The incumbent will be accountable for the design, development, deployment and maintenance of multi-agent AI platforms, including agent orchestration workflows, RAG implementations, vector database management, and AI-driven analytics solutions.

Key Responsibilities:

Familiarize with Ensign's business domain and objectives to develop and deploy data solutions that meet internal business requirements and the needs of partners and customers

Design, develop, test, deploy operational data transformation processes, including async/real-time data processing workflows

Design, develop, manage relational databases and vector databases for AI/ML applications

Design and develop multi-agent AI systems using LangGraph/LangChain for agent orchestration and workflow management

Implement and maintain RAG (Retrieval Augmented Generation) workflows with vector databases (e.g., pgvector, ChromaDB) for semantic search and knowledge retrieval

Integrate LLM APIs and manage prompt engineering for agent behaviors and AI-driven analytics

Provide monitoring, maintenance and support for data operations as part of maintenance & support as required in client projects

Manage development, staging, production environments to provide overall system functionality, health, scalability, resiliency, and security

Deliver detailed documentation and ensure quality throughout project lifecycle

Qualifications/Requirements:

Bachelor's degree in Computer Science / Computer Engineering or equivalent

Strong proficiency in Python programming for data engineering and AI/ML applications, with experience in async/await patterns and concurrent programming

Experience with Bash scripting for automation and system tasks

Experience with AI/ML frameworks such as LangGraph and LangChain for agent orchestration

Experience with vector databases (e.g., pgvector, ChromaDB) and RAG implementation patterns

Basic understanding of REST APIs and async HTTP clients for integrating with external services

Experience with LLM API integration (e.g., Google Gemini, OpenAI) and prompt engineering

Familiarity with Pydantic for data validation and structured data modeling

Understanding of modern software engineering tools such as Git, GitLab

Familiarity with Docker, Kubernetes and cloud services (AWS)

Familiarity with network concepts

Comfort and experience working in Linux environment

Aptitude for automation and software profiling

Proven ability to handle multiple customer projects concurrently

Detail-oriented, solution-focused and problem solver

Willingness to continuously learn and adapt to rapidly evolving AI/ML tools and technologies

Preferred Skills (Good to haves):

Around 1 year of experience developing data engineering pipelines

Experience with Spark, Go, or other data engineering programming languages

Knowledge of different data platforms (e.g. Kafka, MongoDB, Postgres, Elasticsearch), associated tools and cloud-based technologies (e.g. Lambda, Glue)

Have strong knowledge in DevSecOps to design, develop, test, and deploy applications for customer projects

Experience in Cyber Security / Telco industry will be an advantage

Knowledge in Agile and CI/CD is desirable

Familiarity with virtualization platform (Proxmox, VMware, KVM)

Familiarity with Hadoop ecosystem and MPP databases

Ability to demonstrate programming skills and knowledge without being overly dependent on AI