Full Stack Engineer (GenAI & Agentic Solutions) - #1635

JOBSTER PRIVATE LTD.; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

JOBSTER PRIVATE LTD. seeks an experienced software engineer to design and deliver agentic AI workflows and applications. You will embed with business units, prototype rapidly, and iterate with users while building scalable backend services, APIs, and data pipelines.

Responsibilities span data integration, secure engineering, observability, and production readiness. Strong Python, FastAPI, PostgreSQL, and cloud familiarity are essential for impactful delivery.

Qualifications

• 5+ years of software engineering experience, including ownership of production applications from ambiguous requirements through deployment and support.

Responsibilities

• Embed with business units to understand workflows, pain points, data, constraints, and outcomes.

Skills

Backend Engineering

Database Eng

GenAI Systems

Cloud Deliveries

Delivery Mindset

Stakeholder Partnership

5+ Years Experience

Tools

LangGraph

LangChain

n8n

LlamaIndex

Flowise

PostgreSQL

FastAPI

Python

AWS

Bedrock

OpenSearch

Azure

GCP

Job description

Key Responsibilities:

Business Discovery & Solution Shaping: Embed with business units to understand operational workflows, pain points, data, constraints, and intended outcomes. Facilitate discovery sessions, challenge assumptions, and translate needs into prioritised use cases, user stories, solution designs, and measurable success criteria.

Rapid Prototyping & Iterative Delivery: Build working prototypes quickly, validate them with users, and iterate based on evidence. Balance speed with maintainable engineering and take viable solutions through production deployment.

Agentic Workflow Engineering: Design and implement reliable AI workflows and agents using Python-based frameworks and orchestration tools such as LangGraph, LangChain, n8n, or equivalent technologies. Combine deterministic steps, LLM reasoning, tool calling, state management, human approvals, and exception handling as appropriate.

Custom Application Development: Build fit-for-purpose applications around business use cases, including backend services, APIs, integrations, authentication, workflow logic, and lightweight user interfaces where needed.

Data & Knowledge Integration: Design robust data ingestion, transformation, and retrieval pipelines. Integrate enterprise systems, databases, document repositories, APIs, and search or vector services while maintaining data quality, lineage, and access controls.

Backend & Database Engineering: Develop secure, scalable backend services and APIs, and design relational data models using technologies such as Python, FastAPI, and PostgreSQL. Diagnose complex integration, performance, and state-management issues.

AI Quality, Evaluation & Observability: Define evaluation datasets and acceptance criteria; test solution quality, reliability, latency, cost, and tool-call success; implement tracing and monitoring; and continuously improve prompts, retrieval, workflows, and safeguards.

Security, Governance & Responsible AI: Apply secure engineering practices, least-privilege access, data protection, prompt-injection defences, output controls, auditability, and human oversight in line with government policies and the risk profile of each use case.

Deployment, Adoption & Handover: Own production readiness, testing, rollout, documentation, user enablement, support, and knowledge transfer. Track adoption and business outcomes and incorporate field learnings into reusable patterns and improvements to the core platform.

Qualifications:

Experience: 5+ years of software engineering experience, including demonstrated ownership of production applications from ambiguous requirements through deployment and support.

Backend Engineering: Strong proficiency in Python or another modern backend language, API design, asynchronous processing, integration patterns, testing, debugging, and system architecture.

Database & Data Engineering: Strong experience with relational databases, preferably PostgreSQL, including data modelling and query optimisation; practical knowledge of data pipelines, search, and vector retrieval is also required.

GenAI & Agentic Systems: Hands-on experience building LLM-enabled applications, RAG solutions, tool-calling agents, or automated workflows using frameworks such as LangGraph, LangChain, LlamaIndex, n8n, or equivalent.

Cloud & Production Delivery: Practical experience deploying and operating cloud-native applications. Familiarity with AWS and services such as Bedrock and OpenSearch is preferred, although equivalent Azure or GCP experience is acceptable.

Stakeholder Partnership: Strong communication and facilitation skills, with the ability to work directly with non-technical users, clarify business needs, explain trade-offs, manage expectations, and drive adoption.

Delivery Mindset: Comfortable working in ambiguous environments, learning unfamiliar business domains quickly, and balancing user value, delivery speed, security, reliability, and maintainability.

Bonus Points:

Forward Deployment: Experience in consulting delivery, solutions engineering, internal product delivery, or another role involving direct collaboration with users and end-to-end implementation.

Workflow Automation: Experience with visual workflow builders such as n8n or Flowise, including custom nodes, integrations, credential handling, and operational support.

Evaluation & Observability: Experience with LLM evaluation, tracing, observability, red-teaming, or quality assurance tools and methods.

Regulated Environments: Experience delivering applications subject to stringent data privacy, cybersecurity, accessibility, or government requirements, including IM8 policies.